NeurIPS(NIPS) 2020 论文列表
Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
|
Limits to Depth Efficiencies of Self-Attention.
Sampling-Decomposable Generative Adversarial Recommender.
Passport-aware Normalization for Deep Model Protection.
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning.
Distributed Distillation for On-Device Learning.
Manifold GPLVMs for discovering non-Euclidean latent structure in neural data.
Can the Brain Do Backpropagation? - Exact Implementation of Backpropagation in Predictive Coding Networks.
An Analysis of SVD for Deep Rotation Estimation.
Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping.
Multi-agent Trajectory Prediction with Fuzzy Query Attention.
Wasserstein Distances for Stereo Disparity Estimation.
Faithful Embeddings for Knowledge Base Queries.
Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning.
Variational Interaction Information Maximization for Cross-domain Disentanglement.
MeshSDF: Differentiable Iso-Surface Extraction.
Matrix Inference and Estimation in Multi-Layer Models.
PLANS: Neuro-Symbolic Program Learning from Videos.
Multiparameter Persistence Image for Topological Machine Learning.
De-Anonymizing Text by Fingerprinting Language Generation.
Faster DBSCAN via subsampled similarity queries.
Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes.
Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret.
Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks.
Scalable Belief Propagation via Relaxed Scheduling.
Synthesizing Tasks for Block-based Programming.
Learning to Adapt to Evolving Domains.
Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity.
Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games.
Model Class Reliance for Random Forests.
Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning.
Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs.
Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization.
Learning from Label Proportions: A Mutual Contamination Framework.
Big Self-Supervised Models are Strong Semi-Supervised Learners.
Measuring Systematic Generalization in Neural Proof Generation with Transformers.
A Dynamical Central Limit Theorem for Shallow Neural Networks.
Auditing Differentially Private Machine Learning: How Private is Private SGD?
Focus of Attention Improves Information Transfer in Visual Features.
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.
MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models.
Hierarchical Neural Architecture Search for Deep Stereo Matching.
Texture Interpolation for Probing Visual Perception.
Towards Understanding Hierarchical Learning: Benefits of Neural Representations.
Open Graph Benchmark: Datasets for Machine Learning on Graphs.
Gradient Boosted Normalizing Flows.
Graph Random Neural Networks for Semi-Supervised Learning on Graphs.
Set2Graph: Learning Graphs From Sets.
Learning Individually Inferred Communication for Multi-Agent Cooperation.
On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems.
Model Fusion via Optimal Transport.
High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization.
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation.
SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology.
Learning Latent Space Energy-Based Prior Model.
CrossTransformers: spatially-aware few-shot transfer.
Attribute Prototype Network for Zero-Shot Learning.
Minibatch Stochastic Approximate Proximal Point Methods.
Denoised Smoothing: A Provable Defense for Pretrained Classifiers.
Beyond Lazy Training for Over-parameterized Tensor Decomposition.
Goal-directed Generation of Discrete Structures with Conditional Generative Models.
Contextual Games: Multi-Agent Learning with Side Information.
Robust Persistence Diagrams using Reproducing Kernels.
Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate.
One-sample Guided Object Representation Disassembling.
Differentiable Causal Discovery from Interventional Data.
Learning Semantic-aware Normalization for Generative Adversarial Networks.
Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion.
Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings.
MOReL: Model-Based Offline Reinforcement Learning.
Hard Negative Mixing for Contrastive Learning.
Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning.
A General Method for Robust Learning from Batches.
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis.
Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects.
First-Order Methods for Large-Scale Market Equilibrium Computation.
Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians.
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation.
AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection.
Strongly Incremental Constituency Parsing with Graph Neural Networks.
The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification.
Fast Transformers with Clustered Attention.
Curriculum By Smoothing.
Neural Unsigned Distance Fields for Implicit Function Learning.
H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks.
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms.
Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion.
High-contrast "gaudy" images improve the training of deep neural network models of visual cortex.
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning.
Quantile Propagation for Wasserstein-Approximate Gaussian Processes.
Robust Federated Learning: The Case of Affine Distribution Shifts.
Reconsidering Generative Objectives For Counterfactual Reasoning.
BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization.
Convergence and Stability of Graph Convolutional Networks on Large Random Graphs.
Active Structure Learning of Causal DAGs via Directed Clique Trees.
User-Dependent Neural Sequence Models for Continuous-Time Event Data.
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them.
Energy-based Out-of-distribution Detection.
A novel variational form of the Schatten-$p$ quasi-norm.
Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters.
Geometric Dataset Distances via Optimal Transport.
No-regret Learning in Price Competitions under Consumer Reference Effects.
Avoiding Side Effects in Complex Environments.
Personalized Federated Learning with Moreau Envelopes.
A Topological Filter for Learning with Label Noise.
On the distance between two neural networks and the stability of learning.
ContraGAN: Contrastive Learning for Conditional Image Generation.
How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?
The Statistical Cost of Robust Kernel Hyperparameter Turning.
A Group-Theoretic Framework for Data Augmentation.
Efficient Clustering for Stretched Mixtures: Landscape and Optimality.
RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor.
Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning.
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning.
Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality.
A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings.
Sharper Generalization Bounds for Pairwise Learning.
Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization.
Learning to Learn with Feedback and Local Plasticity.
Uncertainty-aware Self-training for Few-shot Text Classification.
POMO: Policy Optimization with Multiple Optima for Reinforcement Learning.
Implicit Regularization in Deep Learning May Not Be Explainable by Norms.
Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking.
On Convergence and Generalization of Dropout Training.
Regret in Online Recommendation Systems.
Escaping the Gravitational Pull of Softmax.
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment.
Hypersolvers: Toward Fast Continuous-Depth Models.
WOR and p's: Sketches for ℓp-Sampling Without Replacement.
CircleGAN: Generative Adversarial Learning across Spherical Circles.
Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions.
Self-training Avoids Using Spurious Features Under Domain Shift.
Fair Hierarchical Clustering.
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features.
Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations.
Learning by Minimizing the Sum of Ranked Range.
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection.
Sparse and Continuous Attention Mechanisms.
Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula.
Learning discrete distributions: user vs item-level privacy.
Train-by-Reconnect: Decoupling Locations of Weights from Their Values.
High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds.
The Cone of Silence: Speech Separation by Localization.
A Self-Tuning Actor-Critic Algorithm.
Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction.
Linearly Converging Error Compensated SGD.
Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems.
Gradient-EM Bayesian Meta-Learning.
The Generalization-Stability Tradeoff In Neural Network Pruning.
Adversarial Attacks on Deep Graph Matching.
Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher.
Probabilistic Active Meta-Learning.
Statistical and Topological Properties of Sliced Probability Divergences.
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability.
Curvature Regularization to Prevent Distortion in Graph Embedding.
Tight last-iterate convergence rates for no-regret learning in multi-player games.
Meta-Learning with Adaptive Hyperparameters.
Top-KAST: Top-K Always Sparse Training.
A Computational Separation between Private Learning and Online Learning.
Meta-Learning through Hebbian Plasticity in Random Networks.
Finding All $\epsilon$-Good Arms in Stochastic Bandits.
Deep Diffusion-Invariant Wasserstein Distributional Classification.
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder.
Learning from Failure: De-biasing Classifier from Biased Classifier.
Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation.
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method.
Online Optimization with Memory and Competitive Control.
Optimally Deceiving a Learning Leader in Stackelberg Games.
Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation.
Unsupervised Translation of Programming Languages.
Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay.
Why Normalizing Flows Fail to Detect Out-of-Distribution Data.
Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems.
On Completeness-aware Concept-Based Explanations in Deep Neural Networks.
A Limitation of the PAC-Bayes Framework.
Information-theoretic Task Selection for Meta-Reinforcement Learning.
Differentiable Top-k with Optimal Transport.
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation.
3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data.
Agnostic Learning with Multiple Objectives.
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference.
Adaptive Online Estimation of Piecewise Polynomial Trends.
The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise.
Graph Information Bottleneck.
Online Learning with Primary and Secondary Losses.
Position-based Scaled Gradient for Model Quantization and Pruning.
Online Matrix Completion with Side Information.
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot.
Movement Pruning: Adaptive Sparsity by Fine-Tuning.
Consistent Plug-in Classifiers for Complex Objectives and Constraints.
Learning Parities with Neural Networks.
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond.
Early-Learning Regularization Prevents Memorization of Noisy Labels.
Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising.
A Study on Encodings for Neural Architecture Search.
Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses.
Factorizable Graph Convolutional Networks.
Instance Based Approximations to Profile Maximum Likelihood.
Latent Template Induction with Gumbel-CRFs.
Improving Sparse Vector Technique with Renyi Differential Privacy.
Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games.
Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge.
A mean-field analysis of two-player zero-sum games.
Confidence sequences for sampling without replacement.
A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval.
A Simple Language Model for Task-Oriented Dialogue.
PIE-NET: Parametric Inference of Point Cloud Edges.
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis.
TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search.
Bayesian Optimization of Risk Measures.
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms.
A Class of Algorithms for General Instrumental Variable Models.
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs.
The Primal-Dual method for Learning Augmented Algorithms.
Regression with reject option and application to kNN.
On the universality of deep learning.
The Complete Lasso Tradeoff Diagram.
OrganITE: Optimal transplant donor organ offering using an individual treatment effect.
A Theoretical Framework for Target Propagation.
A General Large Neighborhood Search Framework for Solving Integer Linear Programs.
GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs.
Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data.
Learning Retrospective Knowledge with Reverse Reinforcement Learning.
Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks.
Beta R-CNN: Looking into Pedestrian Detection from Another Perspective.
Adversarial Bandits with Corruptions: Regret Lower Bound and No-regret Algorithm.
Joint Policy Search for Multi-agent Collaboration with Imperfect Information.
Estimating Training Data Influence by Tracing Gradient Descent.
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning.
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes.
Reinforcement Learning with Augmented Data.
Weston-Watkins Hinge Loss and Ordered Partitions.
A Benchmark for Systematic Generalization in Grounded Language Understanding.
Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition.
Graph Stochastic Neural Networks for Semi-supervised Learning.
A Robust Functional EM Algorithm for Incomplete Panel Count Data.
The Adaptive Complexity of Maximizing a Gross Substitutes Valuation.
Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs.
Comparator-Adaptive Convex Bandits.
EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning.
Accelerating Reinforcement Learning through GPU Atari Emulation.
Universal Function Approximation on Graphs.
Wisdom of the Ensemble: Improving Consistency of Deep Learning Models.
Learning Linear Programs from Optimal Decisions.
Learning Disentangled Representations and Group Structure of Dynamical Environments.
Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs.
Counterfactual Prediction for Bundle Treatment.
What Do Neural Networks Learn When Trained With Random Labels?
Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory.
NVAE: A Deep Hierarchical Variational Autoencoder.
HYDRA: Pruning Adversarially Robust Neural Networks.
Flexible mean field variational inference using mixtures of non-overlapping exponential families.
Recursive Inference for Variational Autoencoders.
Parameterized Explainer for Graph Neural Network.
Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond.
Autoencoders that don't overfit towards the Identity.
An Efficient Framework for Clustered Federated Learning.
Exponential ergodicity of mirror-Langevin diffusions.
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space.
Space-Time Correspondence as a Contrastive Random Walk.
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks.
Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests.
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search.
Asymptotically Optimal Exact Minibatch Metropolis-Hastings.
Quantized Variational Inference.
Throughput-Optimal Topology Design for Cross-Silo Federated Learning.
Online Learning in Contextual Bandits using Gated Linear Networks.
Dual-Free Stochastic Decentralized Optimization with Variance Reduction.
Untangling tradeoffs between recurrence and self-attention in artificial neural networks.
Neural Networks with Small Weights and Depth-Separation Barriers.
TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation.
A new convergent variant of Q-learning with linear function approximation.
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement.
Near-Optimal Comparison Based Clustering.
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization.
Self-Adaptive Training: beyond Empirical Risk Minimization.
Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets.
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems.
COPT: Coordinated Optimal Transport on Graphs.
Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings.
Provably Robust Metric Learning.
Rethinking the Value of Labels for Improving Class-Imbalanced Learning.
Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift.
Weakly Supervised Deep Functional Maps for Shape Matching.
BayReL: Bayesian Relational Learning for Multi-omics Data Integration.
Online Bayesian Goal Inference for Boundedly Rational Planning Agents.
Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics.
Transferable Calibration with Lower Bias and Variance in Domain Adaptation.
Linear-Sample Learning of Low-Rank Distributions.
Semialgebraic Optimization for Lipschitz Constants of ReLU Networks.
Efficient Learning of Generative Models via Finite-Difference Score Matching.
Efficient Planning in Large MDPs with Weak Linear Function Approximation.
Modeling Shared responses in Neuroimaging Studies through MultiView ICA.
Fair regression via plug-in estimator and recalibration with statistical guarantees.
The Generalized Lasso with Nonlinear Observations and Generative Priors.
HRN: A Holistic Approach to One Class Learning.
MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles.
Improving Auto-Augment via Augmentation-Wise Weight Sharing.
Handling Missing Data with Graph Representation Learning.
Avoiding Side Effects By Considering Future Tasks.
Acceleration with a Ball Optimization Oracle.
Fast Unbalanced Optimal Transport on a Tree.
Provable Overlapping Community Detection in Weighted Graphs.
Time-Reversal Symmetric ODE Network.
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks.
Hedging in games: Faster convergence of external and swap regrets.
ColdGANs: Taming Language GANs with Cautious Sampling Strategies.
Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation.
Experimental design for MRI by greedy policy search.
Almost Surely Stable Deep Dynamics.
Content Provider Dynamics and Coordination in Recommendation Ecosystems.
Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks.
Tensor Completion Made Practical.
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev.
Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity.
R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making.
Task-Robust Model-Agnostic Meta-Learning.
One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers.
Modern Hopfield Networks and Attention for Immune Repertoire Classification.
Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding.
Interpretable Sequence Learning for Covid-19 Forecasting.
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients.
Preference-based Reinforcement Learning with Finite-Time Guarantees.
Deep Metric Learning with Spherical Embedding.
Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows.
ICNet: Intra-saliency Correlation Network for Co-Saliency Detection.
Collegial Ensembles.
Neural Non-Rigid Tracking.
Weak Form Generalized Hamiltonian Learning.
Learning Agent Representations for Ice Hockey.
Meta-trained agents implement Bayes-optimal agents.
Learning Optimal Representations with the Decodable Information Bottleneck.
Supervised Contrastive Learning.
Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings.
DisARM: An Antithetic Gradient Estimator for Binary Latent Variables.
Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model.
RandAugment: Practical Automated Data Augmentation with a Reduced Search Space.
Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference.
Measuring Robustness to Natural Distribution Shifts in Image Classification.
OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling.
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction.
A Tight Lower Bound and Efficient Reduction for Swap Regret.
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise.
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs.
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks.
All your loss are belong to Bayes.
Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks.
GCN meets GPU: Decoupling "When to Sample" from "How to Sample".
Pre-training via Paraphrasing.
How do fair decisions fare in long-term qualification?
Ensuring Fairness Beyond the Training Data.
CoMIR: Contrastive Multimodal Image Representation for Registration.
A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices.
What if Neural Networks had SVDs?
Choice Bandits.
Batch normalization provably avoids ranks collapse for randomly initialised deep networks.
What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes.
Regularizing Towards Permutation Invariance In Recurrent Models.
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning.
Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization.
BERT Loses Patience: Fast and Robust Inference with Early Exit.
Making Non-Stochastic Control (Almost) as Easy as Stochastic.
Decentralized Accelerated Proximal Gradient Descent.
X-CAL: Explicit Calibration for Survival Analysis.
The MAGICAL Benchmark for Robust Imitation.
Precise expressions for random projections: Low-rank approximation and randomized Newton.
An Improved Analysis of Stochastic Gradient Descent with Momentum.
The Convolution Exponential and Generalized Sylvester Flows.
Improving model calibration with accuracy versus uncertainty optimization.
Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting.
Byzantine Resilient Distributed Multi-Task Learning.
Learning Robust Decision Policies from Observational Data.
Truthful Data Acquisition via Peer Prediction.
Worst-Case Analysis for Randomly Collected Data.
Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods.
3D Self-Supervised Methods for Medical Imaging.
Learning to Prove Theorems by Learning to Generate Theorems.
Decision trees as partitioning machines to characterize their generalization properties.
Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding.
Bi-level Score Matching for Learning Energy-based Latent Variable Models.
WoodFisher: Efficient Second-Order Approximation for Neural Network Compression.
Hybrid Models for Learning to Branch.
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces.
Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data.
Effective Diversity in Population Based Reinforcement Learning.
Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees.
Distributed Newton Can Communicate Less and Resist Byzantine Workers.
DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling.
Inverse Learning of Symmetries.
Learning to Play No-Press Diplomacy with Best Response Policy Iteration.
Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment.
Fair Multiple Decision Making Through Soft Interventions.
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search.
On the Role of Sparsity and DAG Constraints for Learning Linear DAGs.
Stochastic Stein Discrepancies.
PAC-Bayesian Bound for the Conditional Value at Risk.
Digraph Inception Convolutional Networks.
Neural Anisotropy Directions.
Adversarially Robust Few-Shot Learning: A Meta-Learning Approach.
Replica-Exchange Nosé-Hoover Dynamics for Bayesian Learning on Large Datasets.
Robust large-margin learning in hyperbolic space.
Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization.
Learning outside the Black-Box: The pursuit of interpretable models.
Robustness of Community Detection to Random Geometric Perturbations.
On Reward-Free Reinforcement Learning with Linear Function Approximation.
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting.
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies.
Online Multitask Learning with Long-Term Memory.
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting.
Continuous Regularized Wasserstein Barycenters.
Axioms for Learning from Pairwise Comparisons.
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization.
SOLOv2: Dynamic and Fast Instance Segmentation.
Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations.
ARMA Nets: Expanding Receptive Field for Dense Prediction.
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis.
The All-or-Nothing Phenomenon in Sparse Tensor PCA.
Online Meta-Critic Learning for Off-Policy Actor-Critic Methods.
A convex optimization formulation for multivariate regression.
Learning to Mutate with Hypergradient Guided Population.
Pruning Filter in Filter.
A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods.
Learning Invariances in Neural Networks from Training Data.
Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets.
A mathematical theory of cooperative communication.
Continuous Meta-Learning without Tasks.
CO-Optimal Transport.
Neural Manifold Ordinary Differential Equations.
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models.
SGD with shuffling: optimal rates without component convexity and large epoch requirements.
Applications of Common Entropy for Causal Inference.
Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms.
Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs.
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool.
Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization.
Cooperative Heterogeneous Deep Reinforcement Learning.
Real World Games Look Like Spinning Tops.
Discovering Symbolic Models from Deep Learning with Inductive Biases.
Towards Neural Programming Interfaces.
Disentangling by Subspace Diffusion.
The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification.
Unfolding recurrence by Green's functions for optimized reservoir computing.
f-Divergence Variational Inference.
Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization.
Dual-Resolution Correspondence Networks.
Statistical Optimal Transport posed as Learning Kernel Embedding.
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors.
Random Reshuffling: Simple Analysis with Vast Improvements.
Neural Execution Engines: Learning to Execute Subroutines.
Big Bird: Transformers for Longer Sequences.
Succinct and Robust Multi-Agent Communication With Temporal Message Control.
Continuous Surface Embeddings.
Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning.
Co-Tuning for Transfer Learning.
Online Non-Convex Optimization with Imperfect Feedback.
Understanding Global Feature Contributions With Additive Importance Measures.
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits.
Functional Regularization for Representation Learning: A Unified Theoretical Perspective.
Directional convergence and alignment in deep learning.
Calibrated Reliable Regression using Maximum Mean Discrepancy.
Compositional Explanations of Neurons.
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights.
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration.
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks.
Adversarial Sparse Transformer for Time Series Forecasting.
Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables.
Contrastive Learning with Adversarial Examples.
High-Throughput Synchronous Deep RL.
Combining Deep Reinforcement Learning and Search for Imperfect-Information Games.
Identifying Mislabeled Data using the Area Under the Margin Ranking.
Unbalanced Sobolev Descent.
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis.
Design Space for Graph Neural Networks.
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection.
CHIP: A Hawkes Process Model for Continuous-time Networks with Scalable and Consistent Estimation.
A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm.
CryptoNAS: Private Inference on a ReLU Budget.
Dynamic allocation of limited memory resources in reinforcement learning.
Inverting Gradients - How easy is it to break privacy in federated learning?
Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class.
Conformal Symplectic and Relativistic Optimization.
Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint.
Lipschitz-Certifiable Training with a Tight Outer Bound.
Zap Q-Learning With Nonlinear Function Approximation.
Reinforcement Learning with Feedback Graphs.
MPNet: Masked and Permuted Pre-training for Language Understanding.
Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning.
PAC-Bayes Analysis Beyond the Usual Bounds.
Ratio Trace Formulation of Wasserstein Discriminant Analysis.
Linear Dynamical Systems as a Core Computational Primitive.
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection.
Reservoir Computing meets Recurrent Kernels and Structured Transforms.
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization.
Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample.
Decisions, Counterfactual Explanations and Strategic Behavior.
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning.
Probably Approximately Correct Constrained Learning.
AViD Dataset: Anonymized Videos from Diverse Countries.
On the Equivalence between Online and Private Learnability beyond Binary Classification.
Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs.
Predictive coding in balanced neural networks with noise, chaos and delays.
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms.
End-to-End Learning and Intervention in Games.
Learning to Detect Objects with a 1 Megapixel Event Camera.
Finite-Time Analysis for Double Q-learning.
Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning.
Explicit Regularisation in Gaussian Noise Injections.
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds.
Self-Supervised Visual Representation Learning from Hierarchical Grouping.
Relative gradient optimization of the Jacobian term in unsupervised deep learning.
Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition.
Convex optimization based on global lower second-order models.
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning.
Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding.
Gaussian Gated Linear Networks.
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games.
GAN Memory with No Forgetting.
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning.
Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds.
Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings.
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks.
Path Integral Based Convolution and Pooling for Graph Neural Networks.
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough.
A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network.
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds.
Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations.
Bayesian Attention Modules.
DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation.
Cross-validation Confidence Intervals for Test Error.
On Learning Ising Models under Huber's Contamination Model.
Constrained episodic reinforcement learning in concave-convex and knapsack settings.
Stochastic Normalization.
Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning.
Universal Domain Adaptation through Self Supervision.
Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces.
When Counterpoint Meets Chinese Folk Melodies.
Variational Amodal Object Completion.
Fast and Accurate $k$-means++ via Rejection Sampling.
Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling.
Random Walk Graph Neural Networks.
Robust Pre-Training by Adversarial Contrastive Learning.
Online Bayesian Persuasion.
Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations.
An Efficient Adversarial Attack for Tree Ensembles.
Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning.
Improved Guarantees for k-means++ and k-means++ Parallel.
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding.
Skeleton-bridged Point Completion: From Global Inference to Local Adjustment.
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels.
Domain Generalization via Entropy Regularization.
Certifiably Adversarially Robust Detection of Out-of-Distribution Data.
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning.
Coded Sequential Matrix Multiplication For Straggler Mitigation.
Understanding and Improving Fast Adversarial Training.
Batched Coarse Ranking in Multi-Armed Bandits.
Variational Bayesian Unlearning.
Inductive Quantum Embedding.
The Diversified Ensemble Neural Network.
Shared Space Transfer Learning for analyzing multi-site fMRI data.
Decentralized Langevin Dynamics for Bayesian Learning.
PLLay: Efficient Topological Layer based on Persistent Landscapes.
On the linearity of large non-linear models: when and why the tangent kernel is constant.
Neural encoding with visual attention.
Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping.
Dark Experience for General Continual Learning: a Strong, Simple Baseline.
Non-Crossing Quantile Regression for Distributional Reinforcement Learning.
On the Expressiveness of Approximate Inference in Bayesian Neural Networks.
Few-shot Image Generation with Elastic Weight Consolidation.
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows.
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples.
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity.
The Lottery Ticket Hypothesis for Pre-trained BERT Networks.
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses.
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs.
Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics.
Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences.
Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning.
Consequences of Misaligned AI.
Disentangling Human Error from Ground Truth in Segmentation of Medical Images.
Error Bounds of Imitating Policies and Environments.
A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions.
Learning efficient task-dependent representations with synaptic plasticity.
Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes.
Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing.
The Discrete Gaussian for Differential Privacy.
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding.
Neural Sparse Voxel Fields.
Collapsing Bandits and Their Application to Public Health Intervention.
Sparse Weight Activation Training.
Parametric Instance Classification for Unsupervised Visual Feature learning.
Robustness of Bayesian Neural Networks to Gradient-Based Attacks.
Online Convex Optimization Over Erdos-Renyi Random Networks.
Calibrating CNNs for Lifelong Learning.
Kernel Alignment Risk Estimator: Risk Prediction from Training Data.
A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms.
StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks.
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection.
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs.
Improved Analysis of Clipping Algorithms for Non-convex Optimization.
Markovian Score Climbing: Variational Inference with KL(p||q).
Model Interpretability through the lens of Computational Complexity.
BOSS: Bayesian Optimization over String Spaces.
Active Invariant Causal Prediction: Experiment Selection through Stability.
Efficient Algorithms for Device Placement of DNN Graph Operators.
System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina.
Certified Monotonic Neural Networks.
Robust Sequence Submodular Maximization.
Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates.
Neural Sparse Representation for Image Restoration.
Why are Adaptive Methods Good for Attention Models?
Deep Rao-Blackwellised Particle Filters for Time Series Forecasting.
Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning.
Learning Augmented Energy Minimization via Speed Scaling.
First Order Constrained Optimization in Policy Space.
A kernel test for quasi-independence.
Information Theoretic Regret Bounds for Online Nonlinear Control.
Optimizing Mode Connectivity via Neuron Alignment.
Calibrating Deep Neural Networks using Focal Loss.
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss.
Learning Strategy-Aware Linear Classifiers.
Meta-Gradient Reinforcement Learning with an Objective Discovered Online.
Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian.
Distributionally Robust Local Non-parametric Conditional Estimation.
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation.
Learning to Incentivize Other Learning Agents.
Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition.
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors.
Supermasks in Superposition.
Finite Versus Infinite Neural Networks: an Empirical Study.
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control.
COBE: Contextualized Object Embeddings from Narrated Instructional Video.
Sharp uniform convergence bounds through empirical centralization.
Distributionally Robust Federated Averaging.
A Randomized Algorithm to Reduce the Support of Discrete Measures.
A Fair Classifier Using Kernel Density Estimation.
The Autoencoding Variational Autoencoder.
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering.
Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach.
Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping.
Learning to Select Best Forecast Tasks for Clinical Outcome Prediction.
Online learning with dynamics: A minimax perspective.
Online Adaptation for Consistent Mesh Reconstruction in the Wild.
Learning Feature Sparse Principal Subspace.
A Biologically Plausible Neural Network for Slow Feature Analysis.
Adversarial Training is a Form of Data-dependent Operator Norm Regularization.
See, Hear, Explore: Curiosity via Audio-Visual Association.
Bayesian Pseudocoresets.
Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks.
Deep Evidential Regression.
All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation.
Understanding and Exploring the Network with Stochastic Architectures.
Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs.
Coresets via Bilevel Optimization for Continual Learning and Streaming.
Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations.
Efficient Clustering Based On A Unified View Of $K$-means And Ratio-cut.
A Variational Approach for Learning from Positive and Unlabeled Data.
STEER : Simple Temporal Regularization For Neural ODE.
When Do Neural Networks Outperform Kernel Methods?
AdaTune: Adaptive Tensor Program Compilation Made Efficient.
Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis.
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement.
Entropic Causal Inference: Identifiability and Finite Sample Results.
Task-Oriented Feature Distillation.
Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning.
Implicit Rank-Minimizing Autoencoder.
Learning Sparse Prototypes for Text Generation.
A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints.
Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning.
Recovery of sparse linear classifiers from mixture of responses.
Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning.
Efficient Generation of Structured Objects with Constrained Adversarial Networks.
Black-Box Optimization with Local Generative Surrogates.
Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples.
Reducing Adversarially Robust Learning to Non-Robust PAC Learning.
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks.
STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks.
The Strong Screening Rule for SLOPE.
Assisted Learning: A Framework for Multi-Organization Learning.
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning.
Scalable Graph Neural Networks via Bidirectional Propagation.
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate.
Learning the Linear Quadratic Regulator from Nonlinear Observations.
Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms.
KFC: A Scalable Approximation Algorithm for $k$-center Fair Clustering.
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks.
Planning with General Objective Functions: Going Beyond Total Rewards.
CoinPress: Practical Private Mean and Covariance Estimation.
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler.
Fast geometric learning with symbolic matrices.
Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness.
Spike and slab variational Bayes for high dimensional logistic regression.
Kernel Methods Through the Roof: Handling Billions of Points Efficiently.
Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting.
Organizing recurrent network dynamics by task-computation to enable continual learning.
Meta-Consolidation for Continual Learning.
Adversarial Attacks on Linear Contextual Bandits.
Point process models for sequence detection in high-dimensional neural spike trains.
Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition.
Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency.
Prediction with Corrupted Expert Advice.
Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities.
Deep Inverse Q-learning with Constraints.
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network.
Transfer Learning via ℓ1 Regularization.
DISK: Learning local features with policy gradient.
Rational neural networks.
Learning Utilities and Equilibria in Non-Truthful Auctions.
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay.
GradAug: A New Regularization Method for Deep Neural Networks.
3D Shape Reconstruction from Vision and Touch.
Mutual exclusivity as a challenge for deep neural networks.
Practical Low-Rank Communication Compression in Decentralized Deep Learning.
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning.
Building powerful and equivariant graph neural networks with structural message-passing.
MOPO: Model-based Offline Policy Optimization.
Calibration of Shared Equilibria in General Sum Partially Observable Markov Games.
Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms.
Graph Cross Networks with Vertex Infomax Pooling.
Neural FFTs for Universal Texture Image Synthesis.
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge.
NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity.
Using noise to probe recurrent neural network structure and prune synapses.
Learning Deep Attribution Priors Based On Prior Knowledge.
Online Planning with Lookahead Policies.
Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping.
Smoothly Bounding User Contributions in Differential Privacy.
Directional Pruning of Deep Neural Networks.
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity.
Self-Imitation Learning via Generalized Lower Bound Q-learning.
Learning sparse codes from compressed representations with biologically plausible local wiring constraints.
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent.
RANet: Region Attention Network for Semantic Segmentation.
Constant-Expansion Suffices for Compressed Sensing with Generative Priors.
Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations.
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency.
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints.
Learning Bounds for Risk-sensitive Learning.
Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces.
Transferable Graph Optimizers for ML Compilers.
A Discrete Variational Recurrent Topic Model without the Reparametrization Trick.
MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics.
Equivariant Networks for Hierarchical Structures.
Identifying signal and noise structure in neural population activity with Gaussian process factor models.
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers.
Understanding Gradient Clipping in Private SGD: A Geometric Perspective.
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis.
Group-Fair Online Allocation in Continuous Time.
Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech.
The Potts-Ising model for discrete multivariate data.
Convolutional Tensor-Train LSTM for Spatio-Temporal Learning.
Deep Automodulators.
CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations.
Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions.
A Local Temporal Difference Code for Distributional Reinforcement Learning.
Multi-agent active perception with prediction rewards.
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms.
Smoothed Geometry for Robust Attribution.
Fairness in Streaming Submodular Maximization: Algorithms and Hardness.
Neurosymbolic Transformers for Multi-Agent Communication.
Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals.
Efficient Learning of Discrete Graphical Models.
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder.
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training.
Evolving Normalization-Activation Layers.
Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control.
Adversarial Counterfactual Learning and Evaluation for Recommender System.
Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method.
A Convolutional Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction.
VarGrad: A Low-Variance Gradient Estimator for Variational Inference.
Linear Time Sinkhorn Divergences using Positive Features.
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks.
Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions.
Is normalization indispensable for training deep neural network?
Latent Bandits Revisited.
Group Contextual Encoding for 3D Point Clouds.
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning.
Robust Disentanglement of a Few Factors at a Time.
Instance-wise Feature Grouping.
A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks.
The interplay between randomness and structure during learning in RNNs.
Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement.
Sample Complexity of Uniform Convergence for Multicalibration.
Learning compositional functions via multiplicative weight updates.
Video Frame Interpolation without Temporal Priors.
Linear Disentangled Representations and Unsupervised Action Estimation.
Instance Selection for GANs.
Reliable Graph Neural Networks via Robust Aggregation.
Principal Neighbourhood Aggregation for Graph Nets.
Program Synthesis with Pragmatic Communication.
Interferobot: aligning an optical interferometer by a reinforcement learning agent.
On Infinite-Width Hypernetworks.
Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction.
Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications.
Node Embeddings and Exact Low-Rank Representations of Complex Networks.
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps.
Exemplar Guided Active Learning.
POMDPs in Continuous Time and Discrete Spaces.
Language-Conditioned Imitation Learning for Robot Manipulation Tasks.
Self-Learning Transformations for Improving Gaze and Head Redirection.
Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning.
Deep Energy-based Modeling of Discrete-Time Physics.
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift.
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations.
A Spectral Energy Distance for Parallel Speech Synthesis.
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design.
Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN.
EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints.
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network.
The phase diagram of approximation rates for deep neural networks.
Sample complexity and effective dimension for regression on manifolds.
CompRess: Self-Supervised Learning by Compressing Representations.
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning.
Debiasing Averaged Stochastic Gradient Descent to handle missing values.
Autofocused oracles for model-based design.
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation.
Fully Dynamic Algorithm for Constrained Submodular Optimization.
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration.
Reward Propagation Using Graph Convolutional Networks.
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks.
Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization.
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model.
Practical No-box Adversarial Attacks against DNNs.
ConvBERT: Improving BERT with Span-based Dynamic Convolution.
Uncertainty Aware Semi-Supervised Learning on Graph Data.
Non-parametric Models for Non-negative Functions.
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning.
CogLTX: Applying BERT to Long Texts.
Testing Determinantal Point Processes.
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA.
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty.
Probabilistic Fair Clustering.
Multi-Stage Influence Function.
Incorporating Interpretable Output Constraints in Bayesian Neural Networks.
Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes.
Learning Causal Effects via Weighted Empirical Risk Minimization.
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows.
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators.
Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models.
Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time.
Joint Contrastive Learning with Infinite Possibilities.
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes.
High-recall causal discovery for autocorrelated time series with latent confounders.
Efficient estimation of neural tuning during naturalistic behavior.
CSER: Communication-efficient SGD with Error Reset.
How many samples is a good initial point worth in Low-rank Matrix Recovery?
Generative Neurosymbolic Machines.
Self-Supervised Graph Transformer on Large-Scale Molecular Data.
Contrastive learning of global and local features for medical image segmentation with limited annotations.
Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments.
On Convergence of Nearest Neighbor Classifiers over Feature Transformations.
Dynamic Regret of Convex and Smooth Functions.
Value-driven Hindsight Modelling.
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients.
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs.
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations.
Improved Techniques for Training Score-Based Generative Models.
Matérn Gaussian Processes on Riemannian Manifolds.
Escaping Saddle-Point Faster under Interpolation-like Conditions.
Off-Policy Imitation Learning from Observations.
Investigating Gender Bias in Language Models Using Causal Mediation Analysis.
Temporal Variability in Implicit Online Learning.
Universally Quantized Neural Compression.
The Wasserstein Proximal Gradient Algorithm.
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space.
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization.
Kernel Based Progressive Distillation for Adder Neural Networks.
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax.
Locally Differentially Private (Contextual) Bandits Learning.
Learning Black-Box Attackers with Transferable Priors and Query Feedback.
Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling.
Causal Imitation Learning With Unobserved Confounders.
Minimax Estimation of Conditional Moment Models.
Few-Cost Salient Object Detection with Adversarial-Paced Learning.
PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks.
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method.
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization.
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses.
How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning.
Safe Reinforcement Learning via Curriculum Induction.
Improving Neural Network Training in Low Dimensional Random Bases.
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training.
Deeply Learned Spectral Total Variation Decomposition.
Training Generative Adversarial Networks with Limited Data.
Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation.
MetaPoison: Practical General-purpose Clean-label Data Poisoning.
A Bandit Learning Algorithm and Applications to Auction Design.
Neural Architecture Generator Optimization.
Neural Topographic Factor Analysis for fMRI Data.
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation.
Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks.
Guiding Deep Molecular Optimization with Genetic Exploration.
Rethinking Importance Weighting for Deep Learning under Distribution Shift.
Implicit Graph Neural Networks.
On the Trade-off between Adversarial and Backdoor Robustness.
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology.
A Novel Approach for Constrained Optimization in Graphical Models.
Counterexample-Guided Learning of Monotonic Neural Networks.
A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning.
High-Fidelity Generative Image Compression.
Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization.
Predictive Information Accelerates Learning in RL.
Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits.
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning.
Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning.
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances.
A shooting formulation of deep learning.
Distributional Robustness with IPMs and links to Regularization and GANs.
DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs.
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity.
Online Decision Based Visual Tracking via Reinforcement Learning.
Softmax Deep Double Deterministic Policy Gradients.
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration.
Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery.
Task-agnostic Exploration in Reinforcement Learning.
In search of robust measures of generalization.
MCUNet: Tiny Deep Learning on IoT Devices.
Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web.
Manifold structure in graph embeddings.
Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations.
Deep active inference agents using Monte-Carlo methods.
Hierarchical Granularity Transfer Learning.
Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models.
Proximal Mapping for Deep Regularization.
Sparse Learning with CART.
A polynomial-time algorithm for learning nonparametric causal graphs.
Look-ahead Meta Learning for Continual Learning.
Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning.
Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations.
Deep Smoothing of the Implied Volatility Surface.
Improving robustness against common corruptions by covariate shift adaptation.
Object-Centric Learning with Slot Attention.
Learning to solve TV regularised problems with unrolled algorithms.
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures.
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters.
Adapting to Misspecification in Contextual Bandits.
Coresets for Robust Training of Deep Neural Networks against Noisy Labels.
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images.
An implicit function learning approach for parametric modal regression.
JAX MD: A Framework for Differentiable Physics.
Compositional Generalization by Learning Analytical Expressions.
Joints in Random Forests.
Adversarial robustness via robust low rank representations.
Winning the Lottery with Continuous Sparsification.
Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses.
Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming.
Smooth And Consistent Probabilistic Regression Trees.
Instance-based Generalization in Reinforcement Learning.
Fairness constraints can help exact inference in structured prediction.
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID.
RD$^2$: Reward Decomposition with Representation Decomposition.
TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning.
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs.
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining.
RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist.
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data.
GreedyFool: Distortion-Aware Sparse Adversarial Attack.
Metric-Free Individual Fairness in Online Learning.
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces.
Stage-wise Conservative Linear Bandits.
On Adaptive Distance Estimation.
SnapBoost: A Heterogeneous Boosting Machine.
Modeling and Optimization Trade-off in Meta-learning.
LoCo: Local Contrastive Representation Learning.
Fine-Grained Dynamic Head for Object Detection.
Soft Contrastive Learning for Visual Localization.
Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information.
Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function.
Fair Performance Metric Elicitation.
Phase retrieval in high dimensions: Statistical and computational phase transitions.
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets.
The Smoothed Possibility of Social Choice.
VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain.
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition.
Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions.
Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding.
Learning Some Popular Gaussian Graphical Models without Condition Number Bounds.
Discovering conflicting groups in signed networks.
Robust, Accurate Stochastic Optimization for Variational Inference.
Provably Consistent Partial-Label Learning.
SCOP: Scientific Control for Reliable Neural Network Pruning.
Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing.
GAIT-prop: A biologically plausible learning rule derived from backpropagation of error.
General Transportability of Soft Interventions: Completeness Results.
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks.
SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm.
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation.
Estimating Fluctuations in Neural Representations of Uncertain Environments.
Incorporating BERT into Parallel Sequence Decoding with Adapters.
Learning Compositional Rules via Neural Program Synthesis.
Unsupervised Text Generation by Learning from Search.
A mathematical model for automatic differentiation in machine learning.
Efficient Projection-free Algorithms for Saddle Point Problems.
An Optimal Elimination Algorithm for Learning a Best Arm.
Generalized Leverage Score Sampling for Neural Networks.
Non-Stochastic Control with Bandit Feedback.
High-Dimensional Sparse Linear Bandits.
Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control.
When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes.
Monotone operator equilibrium networks.
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning.
Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth.
FrugalML: How to use ML Prediction APIs more accurately and cheaply.
HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory.
Gibbs Sampling with People.
Constraining Variational Inference with Geometric Jensen-Shannon Divergence.
Non-Euclidean Universal Approximation.
Depth Uncertainty in Neural Networks.
Make One-Shot Video Object Segmentation Efficient Again.
Adaptive Shrinkage Estimation for Streaming Graphs.
SIRI: Spatial Relation Induced Network For Spatial Description Resolution.
Robust Multi-Agent Reinforcement Learning with Model Uncertainty.
Consistency Regularization for Certified Robustness of Smoothed Classifiers.
Semi-Supervised Neural Architecture Search.
Trust the Model When It Is Confident: Masked Model-based Actor-Critic.
Regularizing Black-box Models for Improved Interpretability.
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D.
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding.
Deep Shells: Unsupervised Shape Correspondence with Optimal Transport.
BRP-NAS: Prediction-based NAS using GCNs.
Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form.
Stable and expressive recurrent vision models.
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration.
Provably Efficient Neural GTD for Off-Policy Learning.
Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies.
On the Modularity of Hypernetworks.
A Bayesian Perspective on Training Speed and Model Selection.
Can Graph Neural Networks Count Substructures?
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits.
Deep Subspace Clustering with Data Augmentation.
Incorporating Pragmatic Reasoning Communication into Emergent Language.
Truncated Linear Regression in High Dimensions.
Model Selection in Contextual Stochastic Bandit Problems.
Consistent Structural Relation Learning for Zero-Shot Segmentation.
GPS-Net: Graph-based Photometric Stereo Network.
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs.
Stochastic Optimization with Laggard Data Pipelines.
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point.
AutoBSS: An Efficient Algorithm for Block Stacking Style Search.
An Unbiased Risk Estimator for Learning with Augmented Classes.
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders.
UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging.
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits.
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.
Towards a Better Global Loss Landscape of GANs.
Graph Policy Network for Transferable Active Learning on Graphs.
Model-based Adversarial Meta-Reinforcement Learning.
Simple and Scalable Sparse k-means Clustering via Feature Ranking.
MetaSDF: Meta-Learning Signed Distance Functions.
An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search.
On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression.
Private Identity Testing for High-Dimensional Distributions.
Learning Multi-Agent Communication through Structured Attentive Reasoning.
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching.
Biological credit assignment through dynamic inversion of feedforward networks.
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks.
CoSE: Compositional Stroke Embeddings.
Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding.
Data Diversification: A Simple Strategy For Neural Machine Translation.
Optimal Best-arm Identification in Linear Bandits.
What shapes feature representations? Exploring datasets, architectures, and training.
A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning.
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning.
Self-supervised learning through the eyes of a child.
Information theoretic limits of learning a sparse rule.
Learning Deformable Tetrahedral Meshes for 3D Reconstruction.
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms.
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments.
Continual Learning in Low-rank Orthogonal Subspaces.
Field-wise Learning for Multi-field Categorical Data.
Limits on Testing Structural Changes in Ising Models.
Neuron-level Structured Pruning using Polarization Regularizer.
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization.
GANSpace: Discovering Interpretable GAN Controls.
Approximate Cross-Validation with Low-Rank Data in High Dimensions.
Inference for Batched Bandits.
Dynamic Submodular Maximization.
Generalization Bound of Gradient Descent for Non-Convex Metric Learning.
DynaBERT: Dynamic BERT with Adaptive Width and Depth.
Optimal Query Complexity of Secure Stochastic Convex Optimization.
Self-Supervised Learning by Cross-Modal Audio-Video Clustering.
ShapeFlow: Learnable Deformation Flows Among 3D Shapes.
Provably adaptive reinforcement learning in metric spaces.
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform.
Neural Complexity Measures.
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation.
Federated Bayesian Optimization via Thompson Sampling.
Walsh-Hadamard Variational Inference for Bayesian Deep Learning.
Coherent Hierarchical Multi-Label Classification Networks.
BoxE: A Box Embedding Model for Knowledge Base Completion.
Listening to Sounds of Silence for Speech Denoising.
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data.
Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?
Empirical Likelihood for Contextual Bandits.
Automatically Learning Compact Quality-aware Surrogates for Optimization Problems.
The Pitfalls of Simplicity Bias in Neural Networks.
Exploiting the Surrogate Gap in Online Multiclass Classification.
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning.
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification.
Online Linear Optimization with Many Hints.
Optimal Learning from Verified Training Data.
Learning with Differentiable Pertubed Optimizers.
A Boolean Task Algebra for Reinforcement Learning.
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation.
Universal guarantees for decision tree induction via a higher-order splitting criterion.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.
Color Visual Illusions: A Statistics-based Computational Model.
Learning Rich Rankings.
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction.
Simple and Fast Algorithm for Binary Integer and Online Linear Programming.
CoinDICE: Off-Policy Confidence Interval Estimation.
Projection Robust Wasserstein Distance and Riemannian Optimization.
Minimax Bounds for Generalized Linear Models.
Bayesian Optimization for Iterative Learning.
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures.
Steady State Analysis of Episodic Reinforcement Learning.
Exact Recovery of Mangled Clusters with Same-Cluster Queries.
List-Decodable Mean Estimation via Iterative Multi-Filtering.
Towards Convergence Rate Analysis of Random Forests for Classification.
Optimal visual search based on a model of target detectability in natural images.
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction.
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks.
Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels.
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples.
Kalman Filtering Attention for User Behavior Modeling in CTR Prediction.
Self-Paced Deep Reinforcement Learning.
Smoothed Analysis of Online and Differentially Private Learning.
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data.
Causal Discovery in Physical Systems from Videos.
Finer Metagenomic Reconstruction via Biodiversity Optimization.
Towards Safe Policy Improvement for Non-Stationary MDPs.
Learnability with Indirect Supervision Signals.
Myersonian Regression.
Learning to Learn Variational Semantic Memory.
Learning Mutational Semantics.
Adversarial Learning for Robust Deep Clustering.
Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond.
Is Long Horizon RL More Difficult Than Short Horizon RL?
Matrix Completion with Hierarchical Graph Side Information.
On Regret with Multiple Best Arms.
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games.
Towards a Combinatorial Characterization of Bounded-Memory Learning.
Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits.
Neural Networks Learning and Memorization with (almost) no Over-Parameterization.
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning.
Further Analysis of Outlier Detection with Deep Generative Models.
Learning to Play Sequential Games versus Unknown Opponents.
Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms.
Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach.
Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts.
Adversarial Example Games.
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View.
PEP: Parameter Ensembling by Perturbation.
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals.
Bandit Linear Control.
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring.
Large-Scale Methods for Distributionally Robust Optimization.
Better Full-Matrix Regret via Parameter-Free Online Learning.
Understanding spiking networks through convex optimization.
Impossibility Results for Grammar-Compressed Linear Algebra.
COT-GAN: Generating Sequential Data via Causal Optimal Transport.
Generalized Boosting.
UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree.
Debiased Contrastive Learning.
Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation.
Approximate Cross-Validation for Structured Models.
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning.
Sliding Window Algorithms for k-Clustering Problems.
Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs.
Approximate Heavily-Constrained Learning with Lagrange Multiplier Models.
Adaptive Probing Policies for Shortest Path Routing.
Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation.
Characterizing emergent representations in a space of candidate learning rules for deep networks.
Baxter Permutation Process.
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference.
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks.
Spin-Weighted Spherical CNNs.
Curriculum Learning by Dynamic Instance Hardness.
A Closer Look at Accuracy vs. Robustness.
Factor Graph Neural Networks.
Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe.
Optimal Prediction of the Number of Unseen Species with Multiplicity.
Bad Global Minima Exist and SGD Can Reach Them.
PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals.
Multi-Fidelity Bayesian Optimization via Deep Neural Networks.
Offline Imitation Learning with a Misspecified Simulator.
Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties.
Targeted Adversarial Perturbations for Monocular Depth Prediction.
Zero-Resource Knowledge-Grounded Dialogue Generation.
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks.
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards.
General Control Functions for Causal Effect Estimation from IVs.
Reparameterizing Mirror Descent as Gradient Descent.
Estimation of Skill Distribution from a Tournament.
Certified Defense to Image Transformations via Randomized Smoothing.
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability.
Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes.
Reinforced Molecular Optimization with Neighborhood-Controlled Grammars.
Finding the Homology of Decision Boundaries with Active Learning.
Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning.
Greedy inference with structure-exploiting lazy maps.
Learning the Geometry of Wave-Based Imaging.
Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices.
Theory-Inspired Path-Regularized Differential Network Architecture Search.
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes.
Adversarial Distributional Training for Robust Deep Learning.
From Finite to Countable-Armed Bandits.
An efficient nonconvex reformulation of stagewise convex optimization problems.
Self-Supervised Generative Adversarial Compression.
Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes.
Variational Bayesian Monte Carlo with Noisy Likelihoods.
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL.
Learning Invariants through Soft Unification.
Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud.
Multi-label Contrastive Predictive Coding.
Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice.
Adversarial Blocking Bandits.
Robust Reinforcement Learning via Adversarial training with Langevin Dynamics.
Novelty Search in Representational Space for Sample Efficient Exploration.
Posterior Re-calibration for Imbalanced Datasets.
Cycle-Contrast for Self-Supervised Video Representation Learning.
Towards Learning Convolutions from Scratch.
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search.
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning.
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms.
Demystifying Orthogonal Monte Carlo and Beyond.
Subgraph Neural Networks.
The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models.
Learning from Aggregate Observations.
Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework.
Improving Generalization in Reinforcement Learning with Mixture Regularization.
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree.
Deep Transformation-Invariant Clustering.
Secretary and Online Matching Problems with Machine Learned Advice.
Distributionally Robust Parametric Maximum Likelihood Estimation.
Deep Statistical Solvers.
Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics.
Off-Policy Interval Estimation with Lipschitz Value Iteration.
Neural Star Domain as Primitive Representation.
Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards.
On the Theory of Transfer Learning: The Importance of Task Diversity.
Detecting Hands and Recognizing Physical Contact in the Wild.
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification.
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent.
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows.
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs.
Boosting Adversarial Training with Hypersphere Embedding.
Critic Regularized Regression.
Generalized Hindsight for Reinforcement Learning.
Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study.
Estimating weighted areas under the ROC curve.
No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium.
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks.
ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping.
Language and Visual Entity Relationship Graph for Agent Navigation.
The NetHack Learning Environment.
MRI Banding Removal via Adversarial Training.
Automatic Curriculum Learning through Value Disagreement.
Geometric Exploration for Online Control.
An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods.
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization.
Part-dependent Label Noise: Towards Instance-dependent Label Noise.
Learning Certified Individually Fair Representations.
Heuristic Domain Adaptation.
Differentiable Augmentation for Data-Efficient GAN Training.
Graph Geometry Interaction Learning.
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains.
Hierarchical nucleation in deep neural networks.
Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment.
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness.
Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian.
Rotated Binary Neural Network.
Implicit Neural Representations with Periodic Activation Functions.
Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free.
Online Neural Connectivity Estimation with Noisy Group Testing.
Multi-Plane Program Induction with 3D Box Priors.
Preference learning along multiple criteria: A game-theoretic perspective.
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss.
Generating Correct Answers for Progressive Matrices Intelligence Tests.
A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems.
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method.
Strictly Batch Imitation Learning by Energy-based Distribution Matching.
Exactly Computing the Local Lipschitz Constant of ReLU Networks.
Training Stronger Baselines for Learning to Optimize.
Fair regression with Wasserstein barycenters.
Understanding the Role of Training Regimes in Continual Learning.
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks.
A simple normative network approximates local non-Hebbian learning in the cortex.
Interior Point Solving for LP-based prediction+optimisation.
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning.
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning.
Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE.
Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC.
Self-Supervised Few-Shot Learning on Point Clouds.
Swapping Autoencoder for Deep Image Manipulation.
Efficient active learning of sparse halfspaces with arbitrary bounded noise.
Training Linear Finite-State Machines.
Small Nash Equilibrium Certificates in Very Large Games.
Auxiliary Task Reweighting for Minimum-data Learning.
Implicit Distributional Reinforcement Learning.
Uncertainty Quantification for Inferring Hawkes Networks.
Synthetic Data Generators - Sequential and Private.
Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model.
Neuronal Gaussian Process Regression.
Correlation Robust Influence Maximization.
Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data.
FedSplit: an algorithmic framework for fast federated optimization.
Curriculum learning for multilevel budgeted combinatorial problems.
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction.
Learning Restricted Boltzmann Machines with Sparse Latent Variables.
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection.
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars.
Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization.
Regularized linear autoencoders recover the principal components, eventually.
CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection.
Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions.
Exchangeable Neural ODE for Set Modeling.
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions.
Hierarchical Poset Decoding for Compositional Generalization in Language.
Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence.
Sampling from a k-DPP without looking at all items.
Bandit Samplers for Training Graph Neural Networks.
On Uniform Convergence and Low-Norm Interpolation Learning.
Barking up the right tree: an approach to search over molecule synthesis DAGs.
Denoising Diffusion Probabilistic Models.
What Makes for Good Views for Contrastive Learning?
The Mean-Squared Error of Double Q-Learning.
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables.
Learning Strategic Network Emergence Games.
Online Structured Meta-learning.
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images.
Multipole Graph Neural Operator for Parametric Partial Differential Equations.
Dynamic Regret of Policy Optimization in Non-Stationary Environments.
Probabilistic Linear Solvers for Machine Learning.
On Correctness of Automatic Differentiation for Non-Differentiable Functions.
On Efficiency in Hierarchical Reinforcement Learning.
Neural Controlled Differential Equations for Irregular Time Series.
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization.
Autoregressive Score Matching.
Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs.
Factor Graph Grammars.
Compositional Visual Generation with Energy Based Models.
Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations.
Large-Scale Adversarial Training for Vision-and-Language Representation Learning.
Bootstrapping neural processes.
A Dictionary Approach to Domain-Invariant Learning in Deep Networks.
Towards Scalable Bayesian Learning of Causal DAGs.
Neural Power Units.
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning.
Off-Policy Evaluation via the Regularized Lagrangian.
On the Convergence of Smooth Regularized Approximate Value Iteration Schemes.
Neutralizing Self-Selection Bias in Sampling for Sortition.
Hyperparameter Ensembles for Robustness and Uncertainty Quantification.
A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration.
Introducing Routing Uncertainty in Capsule Networks.
SMYRF - Efficient Attention using Asymmetric Clustering.
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks.
Federated Principal Component Analysis.
Benchmarking Deep Learning Interpretability in Time Series Predictions.
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes.
Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations.
Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems.
Detecting Interactions from Neural Networks via Topological Analysis.
Pruning neural networks without any data by iteratively conserving synaptic flow.
Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality.
From Boltzmann Machines to Neural Networks and Back Again.
The Power of Comparisons for Actively Learning Linear Classifiers.
Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention.
Generative 3D Part Assembly via Dynamic Graph Learning.
Proximity Operator of the Matrix Perspective Function and its Applications.
Multi-task Causal Learning with Gaussian Processes.
Minibatch vs Local SGD for Heterogeneous Distributed Learning.
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo.
Unsupervised Data Augmentation for Consistency Training.
Learning Kernel Tests Without Data Splitting.
Demixed shared component analysis of neural population data from multiple brain areas.
Boundary thickness and robustness in learning models.
On 1/n neural representation and robustness.
Multi-task Batch Reinforcement Learning with Metric Learning.
Wavelet Flow: Fast Training of High Resolution Normalizing Flows.
Neurosymbolic Reinforcement Learning with Formally Verified Exploration.
Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield.
How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions.
Predicting Training Time Without Training.
Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension.
Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers.
Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence.
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision.
Sparse Symplectically Integrated Neural Networks.
Estimating decision tree learnability with polylogarithmic sample complexity.
Meta-learning from Tasks with Heterogeneous Attribute Spaces.
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking.
Learning Physical Graph Representations from Visual Scenes.
Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?
Differentially-Private Federated Linear Bandits.
Revisiting Parameter Sharing for Automatic Neural Channel Number Search.
NeuMiss networks: differentiable programming for supervised learning with missing values.
Model Agnostic Multilevel Explanations.
Random Reshuffling is Not Always Better.
GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification.
Stochastic Normalizing Flows.
Neuron Shapley: Discovering the Responsible Neurons.
On Second Order Behaviour in Augmented Neural ODEs.
Evaluating Attribution for Graph Neural Networks.
Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks.
Stochastic Deep Gaussian Processes over Graphs.
Graph Meta Learning via Local Subgraphs.
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel.
Bayesian Probabilistic Numerical Integration with Tree-Based Models.
Gradient Surgery for Multi-Task Learning.
Graph Contrastive Learning with Augmentations.
Woodbury Transformations for Deep Generative Flows.
Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization.
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers.
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective.
On Testing of Samplers.
Bayesian Bits: Unifying Quantization and Pruning.
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting.
SLIP: Learning to predict in unknown dynamical systems with long-term memory.
Meta-Learning Requires Meta-Augmentation.
Gradient Estimation with Stochastic Softmax Tricks.
Self-supervised Co-Training for Video Representation Learning.
A Catalyst Framework for Minimax Optimization.
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views.
Entrywise convergence of iterative methods for eigenproblems.
Unfolding the Alternating Optimization for Blind Super Resolution.
RepPoints v2: Verification Meets Regression for Object Detection.
Learning of Discrete Graphical Models with Neural Networks.
Training Generative Adversarial Networks by Solving Ordinary Differential Equations.
Policy Improvement via Imitation of Multiple Oracles.
Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks.
Latent World Models For Intrinsically Motivated Exploration.
Structured Convolutions for Efficient Neural Network Design.
The Value Equivalence Principle for Model-Based Reinforcement Learning.
Independent Policy Gradient Methods for Competitive Reinforcement Learning.
Towards practical differentially private causal graph discovery.
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles.
Language Through a Prism: A Spectral Approach for Multiscale Language Representations.
Learning under Model Misspecification: Applications to Variational and Ensemble methods.
Sub-sampling for Efficient Non-Parametric Bandit Exploration.
Generative causal explanations of black-box classifiers.
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry.
Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits.
Agnostic Learning of a Single Neuron with Gradient Descent.
Parabolic Approximation Line Search for DNNs.
Adam with Bandit Sampling for Deep Learning.
Learning to Orient Surfaces by Self-supervised Spherical CNNs.
Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm.
An analytic theory of shallow networks dynamics for hinge loss classification.
Robust Density Estimation under Besov IPM Losses.
Federated Accelerated Stochastic Gradient Descent.
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming.
Robust Quantization: One Model to Rule Them All.
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen.
Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction.
Dirichlet Graph Variational Autoencoder.
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote.
Sparse Graphical Memory for Robust Planning.
Multiscale Deep Equilibrium Models.
Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning.
A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling.
Noise-Contrastive Estimation for Multivariate Point Processes.
Robust Optimization for Fairness with Noisy Protected Groups.
Learning Physical Constraints with Neural Projections.
Certifying Confidence via Randomized Smoothing.
Exact expressions for double descent and implicit regularization via surrogate random design.
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks.
Model Inversion Networks for Model-Based Optimization.
Causal Estimation with Functional Confounders.
Feature Importance Ranking for Deep Learning.
Attribution Preservation in Network Compression for Reliable Network Interpretation.
Decision-Making with Auto-Encoding Variational Bayes.
A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons.
Neural Dynamic Policies for End-to-End Sensorimotor Learning.
Meta-Neighborhoods.
Deep Direct Likelihood Knockoffs.
Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering.
HOI Analysis: Integrating and Decomposing Human-Object Interaction.
Continual Learning of Control Primitives : Skill Discovery via Reset-Games.
Certifying Strategyproof Auction Networks.
Network size and size of the weights in memorization with two-layers neural networks.
Domain Adaptation as a Problem of Inference on Graphical Models.
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method.
Learning Differentiable Programs with Admissible Neural Heuristics.
Stochastic Optimization for Performative Prediction.
Towards Deeper Graph Neural Networks with Differentiable Group Normalization.
Telescoping Density-Ratio Estimation.
Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons.
Probabilistic Orientation Estimation with Matrix Fisher Distributions.
Delay and Cooperation in Nonstochastic Linear Bandits.
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity.
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems.
Deep Multimodal Fusion by Channel Exchanging.
Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence.
Deep Variational Instance Segmentation.
Improved Algorithms for Convex-Concave Minimax Optimization.
On the training dynamics of deep networks with $L_2$ regularization.
Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models.
Multi-Task Reinforcement Learning with Soft Modularization.
Towards More Practical Adversarial Attacks on Graph Neural Networks.
Generative View Synthesis: From Single-view Semantics to Novel-view Images.
Learning Representations from Audio-Visual Spatial Alignment.
Randomized tests for high-dimensional regression: A more efficient and powerful solution.
Unsupervised Learning of Object Landmarks via Self-Training Correspondence.
Bayesian Deep Learning and a Probabilistic Perspective of Generalization.
Robust Meta-learning for Mixed Linear Regression with Small Batches.
A Non-Asymptotic Analysis for Stein Variational Gradient Descent.
Labelling unlabelled videos from scratch with multi-modal self-supervision.
Your Classifier can Secretly Suffice Multi-Source Domain Adaptation.
Probabilistic Circuits for Variational Inference in Discrete Graphical Models.
Privacy Amplification via Random Check-Ins.
Efficient Low Rank Gaussian Variational Inference for Neural Networks.
Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation.
Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice.
Variational Policy Gradient Method for Reinforcement Learning with General Utilities.
AvE: Assistance via Empowerment.
POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis.
Diversity can be Transferred: Output Diversification for White- and Black-box Attacks.
Hierarchical Quantized Autoencoders.
Learning Structured Distributions From Untrusted Batches: Faster and Simpler.
Higher-Order Certification For Randomized Smoothing.
Unsupervised Learning of Dense Visual Representations.
Fast Fourier Convolution.
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning.
Continual Deep Learning by Functional Regularisation of Memorable Past.
Low Distortion Block-Resampling with Spatially Stochastic Networks.
Probabilistic Time Series Forecasting with Shape and Temporal Diversity.
Reward-rational (implicit) choice: A unifying formalism for reward learning.
PAC-Bayes Learning Bounds for Sample-Dependent Priors.
Influence-Augmented Online Planning for Complex Environments.
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses.
Learning Differential Equations that are Easy to Solve.
Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms.
Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations.
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards.
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models.
SuperLoss: A Generic Loss for Robust Curriculum Learning.
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation.
Semantic Visual Navigation by Watching YouTube Videos.
Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing.
Efficient semidefinite-programming-based inference for binary and multi-class MRFs.
Object Goal Navigation using Goal-Oriented Semantic Exploration.
Munchausen Reinforcement Learning.
On the Error Resistance of Hinge-Loss Minimization.
How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods.
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning.
Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization.
Balanced Meta-Softmax for Long-Tailed Visual Recognition.
Learning Loss for Test-Time Augmentation.
Counterfactual Predictions under Runtime Confounding.
Predictive inference is free with the jackknife+-after-bootstrap.
Sequential Bayesian Experimental Design with Variable Cost Structure.
From Predictions to Decisions: Using Lookahead Regularization.
Adaptive Reduced Rank Regression.
Searching for Low-Bit Weights in Quantized Neural Networks.
AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control.
Fairness with Overlapping Groups; a Probabilistic Perspective.
On the Power of Louvain in the Stochastic Block Model.
Differentially Private Clustering: Tight Approximation Ratios.
Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine.
Sufficient dimension reduction for classification using principal optimal transport direction.
Self-Supervised Relational Reasoning for Representation Learning.
Rethinking Learnable Tree Filter for Generic Feature Transform.
Counterfactual Data Augmentation using Locally Factored Dynamics.
Teaching a GAN What Not to Learn.
Dissecting Neural ODEs.
Learning discrete distributions with infinite support.
Learning About Objects by Learning to Interact with Them.
An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch.
OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification.
DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks.
On Warm-Starting Neural Network Training.
CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching.
Adaptive Discretization for Model-Based Reinforcement Learning.
Unsupervised Sound Separation Using Mixture Invariant Training.
Rethinking Pre-training and Self-training.
Submodular Meta-Learning.
On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples.
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks.
Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm.
All Word Embeddings from One Embedding.
Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration.
Variance reduction for Random Coordinate Descent-Langevin Monte Carlo.
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals.
Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow.
Distribution-free binary classification: prediction sets, confidence intervals and calibration.
On ranking via sorting by estimated expected utility.
Deep Reinforcement and InfoMax Learning.
Bidirectional Convolutional Poisson Gamma Dynamical Systems.
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts.
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization.
Natural Graph Networks.
Learning Disentangled Representations of Videos with Missing Data.
Diverse Image Captioning with Context-Object Split Latent Spaces.
Learning to Approximate a Bregman Divergence.
Learning Global Transparent Models consistent with Local Contrastive Explanations.
Classification with Valid and Adaptive Coverage.
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation.
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach.
Robust Correction of Sampling Bias using Cumulative Distribution Functions.
Do Adversarially Robust ImageNet Models Transfer Better?
Restoring Negative Information in Few-Shot Object Detection.
Unsupervised Representation Learning by Invariance Propagation.
Cross-Scale Internal Graph Neural Network for Image Super-Resolution.
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks.
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition.
How hard is to distinguish graphs with graph neural networks?
Input-Aware Dynamic Backdoor Attack.
Inferring learning rules from animal decision-making.
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement.
Online MAP Inference of Determinantal Point Processes.
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases.
An operator view of policy gradient methods.
Modeling Noisy Annotations for Crowd Counting.
Community detection using fast low-cardinality semidefinite programming
.
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators.
Self-Distillation Amplifies Regularization in Hilbert Space.
Ode to an ODE.
Audeo: Audio Generation for a Silent Performance Video.
Breaking the Communication-Privacy-Accuracy Trilemma.
Optimal Private Median Estimation under Minimal Distributional Assumptions.
A Unified View of Label Shift Estimation.
Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs.
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval.
Reinforcement Learning for Control with Multiple Frequencies.
UCLID-Net: Single View Reconstruction in Object Space.
Co-exposure Maximization in Online Social Networks.
Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs.
Compact task representations as a normative model for higher-order brain activity.
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies.
Finite Continuum-Armed Bandits.
Adaptive Gradient Quantization for Data-Parallel SGD.
Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms.
Causal analysis of Covid-19 Spread in Germany.
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances.
Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?
Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization.
Unsupervised object-centric video generation and decomposition in 3D.
A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions.
Learning Graph Structure With A Finite-State Automaton Layer.
Multimodal Graph Networks for Compositional Generalization in Visual Question Answering.
Triple descent and the two kinds of overfitting: where & why do they appear?
Learning Dynamic Belief Graphs to Generalize on Text-Based Games.
Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks.
Fourier Spectrum Discrepancies in Deep Network Generated Images.
Learning to summarize with human feedback.
Normalizing Kalman Filters for Multivariate Time Series Analysis.
Adversarial Self-Supervised Contrastive Learning.
Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes.
Adversarial Weight Perturbation Helps Robust Generalization.
Learning from Mixtures of Private and Public Populations.
Hold me tight! Influence of discriminative features on deep network boundaries.
Logarithmic Pruning is All You Need.
Toward the Fundamental Limits of Imitation Learning.
Partial Optimal Tranport with applications on Positive-Unlabeled Learning.
Partially View-aligned Clustering.
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation.
A/B Testing in Dense Large-Scale Networks: Design and Inference.
Modular Meta-Learning with Shrinkage.
Geometric All-way Boolean Tensor Decomposition.
Implicit Regularization and Convergence for Weight Normalization.
Model-based Policy Optimization with Unsupervised Model Adaptation.
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems.
Intra-Processing Methods for Debiasing Neural Networks.
Network-to-Network Translation with Conditional Invertible Neural Networks.
ShiftAddNet: A Hardware-Inspired Deep Network.
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning.
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization.
Interventional Few-Shot Learning.
Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes.
Dual Instrumental Variable Regression.
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? - A Neural Tangent Kernel Perspective.
Learning abstract structure for drawing by efficient motor program induction.
Improving Policy-Constrained Kidney Exchange via Pre-Screening.
Weakly-Supervised Reinforcement Learning for Controllable Behavior.
Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions.
Identifying Learning Rules From Neural Network Observables.
Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function.
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes.
Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient.
Structured Prediction for Conditional Meta-Learning.
Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model.
Fighting Copycat Agents in Behavioral Cloning from Observation Histories.
PRANK: motion Prediction based on RANKing.
Online Robust Regression via SGD on the l1 loss.
Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance.
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation.
Riemannian Continuous Normalizing Flows.
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance.
Bayesian Robust Optimization for Imitation Learning.
Bayesian Multi-type Mean Field Multi-agent Imitation Learning.
Inverse Reinforcement Learning from a Gradient-based Learner.
Information Maximization for Few-Shot Learning.
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification.
Consistent feature selection for analytic deep neural networks.
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation.
Approximation Based Variance Reduction for Reparameterization Gradients.
Practical Quasi-Newton Methods for Training Deep Neural Networks.
On Power Laws in Deep Ensembles.
Falcon: Fast Spectral Inference on Encrypted Data.
Ensemble Distillation for Robust Model Fusion in Federated Learning.
Stationary Activations for Uncertainty Calibration in Deep Learning.
Deep Imitation Learning for Bimanual Robotic Manipulation.
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework.
Lower Bounds and Optimal Algorithms for Personalized Federated Learning.
Rescuing neural spike train models from bad MLE.
Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification.
Forethought and Hindsight in Credit Assignment.
Faster Wasserstein Distance Estimation with the Sinkhorn Divergence.
Gradient Regularized V-Learning for Dynamic Treatment Regimes.
Pointer Graph Networks.
Rethinking pooling in graph neural networks.
Cross-lingual Retrieval for Iterative Self-Supervised Training.
Towards Problem-dependent Optimal Learning Rates.
Self-Distillation as Instance-Specific Label Smoothing.
Network Diffusions via Neural Mean-Field Dynamics.
Near-Optimal Reinforcement Learning with Self-Play.
Statistical-Query Lower Bounds via Functional Gradients.
Biologically Inspired Mechanisms for Adversarial Robustness.
Differentiable Meta-Learning of Bandit Policies.
Adversarial Robustness of Supervised Sparse Coding.
SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence.
Optimizing Neural Networks via Koopman Operator Theory.
Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward.
Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains.
A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model.
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout.
Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits.
Cooperative Multi-player Bandit Optimization.
Learning Affordance Landscapes for Interaction Exploration in 3D Environments.
The Power of Predictions in Online Control.
On the equivalence of molecular graph convolution and molecular wave function with poor basis set.
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks.
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks.
Projected Stein Variational Gradient Descent.
Marginal Utility for Planning in Continuous or Large Discrete Action Spaces.
MomentumRNN: Integrating Momentum into Recurrent Neural Networks.
Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics.
Margins are Insufficient for Explaining Gradient Boosting.
Language Models are Few-Shot Learners.
Prophet Attention: Predicting Attention with Future Attention.
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback.
Self-Supervised Relationship Probing.
Outlier Robust Mean Estimation with Subgaussian Rates via Stability.
On Numerosity of Deep Neural Networks.
Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS.
Ultra-Low Precision 4-bit Training of Deep Neural Networks.
Efficient Exact Verification of Binarized Neural Networks.
A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees.
Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso.
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows.
Deep Transformers with Latent Depth.
Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction.
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms.
Graphon Neural Networks and the Transferability of Graph Neural Networks.
Compositional Generalization via Neural-Symbolic Stack Machines.
Locally-Adaptive Nonparametric Online Learning.
Ultrahyperbolic Representation Learning.
Online Sinkhorn: Optimal Transport distances from sample streams.
Sinkhorn Natural Gradient for Generative Models.
On Adaptive Attacks to Adversarial Example Defenses.
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning.
Correspondence learning via linearly-invariant embedding.
Distribution Matching for Crowd Counting.
Neural Networks Fail to Learn Periodic Functions and How to Fix It.
Thunder: a Fast Coordinate Selection Solver for Sparse Learning.
UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging.
Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization.
Deep Archimedean Copulas.
Explainable Voting.
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect.
CASTLE: Regularization via Auxiliary Causal Graph Discovery.
Auto Learning Attention.
HiPPO: Recurrent Memory with Optimal Polynomial Projections.
A causal view of compositional zero-shot recognition.
On the Similarity between the Laplace and Neural Tangent Kernels.
A Bayesian Nonparametrics View into Deep Representations.
Assessing SATNet's Ability to Solve the Symbol Grounding Problem.
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits.
Continuous Submodular Maximization: Beyond DR-Submodularity.
A Unifying View of Optimism in Episodic Reinforcement Learning.
No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix.
Recurrent Quantum Neural Networks.
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts.
A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses.
Learning to search efficiently for causally near-optimal treatments.
The Implications of Local Correlation on Learning Some Deep Functions.
FleXOR: Trainable Fractional Quantization.
ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks.
Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming.
Detection as Regression: Certified Object Detection with Median Smoothing.
Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration.
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity.
Understanding Deep Architecture with Reasoning Layer.
Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability.
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation.
Ensembling geophysical models with Bayesian Neural Networks.
Online Influence Maximization under Linear Threshold Model.
Conservative Q-Learning for Offline Reinforcement Learning.
Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity.
Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems.
Adaptation Properties Allow Identification of Optimized Neural Codes.
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond.
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems.
Model Selection for Production System via Automated Online Experiments.
Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering.
Blind Video Temporal Consistency via Deep Video Prior.
Taming Discrete Integration via the Boon of Dimensionality.
Discovering Reinforcement Learning Algorithms.
Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring.
Adaptive Sampling for Stochastic Risk-Averse Learning.
Improved Schemes for Episodic Memory-based Lifelong Learning.
Bayesian Deep Ensembles via the Neural Tangent Kernel.
Coresets for Near-Convex Functions.
Sinkhorn Barycenter via Functional Gradient Descent.
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks.
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning.
Primal-Dual Mesh Convolutional Neural Networks.
Higher-Order Spectral Clustering of Directed Graphs.
Hardness of Learning Neural Networks with Natural Weights.
A Combinatorial Perspective on Transfer Learning.
AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning.
Better Set Representations For Relational Reasoning.
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks.
Convolutional Generation of Textured 3D Meshes.
Deep Structural Causal Models for Tractable Counterfactual Inference.
Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding.
Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization.
Learning Guidance Rewards with Trajectory-space Smoothing.
Towards Better Generalization of Adaptive Gradient Methods.
What went wrong and when? Instance-wise feature importance for time-series black-box models.
Adapting Neural Architectures Between Domains.
Online Algorithm for Unsupervised Sequential Selection with Contextual Information.
The route to chaos in routing games: When is price of anarchy too optimistic?
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian.
Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model.
Fairness without Demographics through Adversarially Reweighted Learning.
Robust compressed sensing using generative models.
Debugging Tests for Model Explanations.
Post-training Iterative Hierarchical Data Augmentation for Deep Networks.
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality.
Belief Propagation Neural Networks.
Causal Intervention for Weakly-Supervised Semantic Segmentation.
Online Agnostic Boosting via Regret Minimization.
Rankmax: An Adaptive Projection Alternative to the Softmax Function.
Towards Playing Full MOBA Games with Deep Reinforcement Learning.
Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing.
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence.
Neuron Merging: Compensating for Pruned Neurons.
Improving Inference for Neural Image Compression.
Exploiting weakly supervised visual patterns to learn from partial annotations.
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction.
Neural Networks with Recurrent Generative Feedback.
Submodular Maximization Through Barrier Functions.
What is being transferred in transfer learning?
One-bit Supervision for Image Classification.
Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network.
Learning Manifold Implicitly via Explicit Heat-Kernel Learning.
Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee.
Simultaneous Preference and Metric Learning from Paired Comparisons.
Flows for simultaneous manifold learning and density estimation.
Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time.
Generalised Bayesian Filtering via Sequential Monte Carlo.
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law.
A Closer Look at the Training Strategy for Modern Meta-Learning.
Hard Shape-Constrained Kernel Machines.
Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates.
Achieving Equalized Odds by Resampling Sensitive Attributes.
Efficient Contextual Bandits with Continuous Actions.
Learning Composable Energy Surrogates for PDE Order Reduction.
Coresets for Regressions with Panel Data.
How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization.
Minimax Classification with 0-1 Loss and Performance Guarantees.
A Causal View on Robustness of Neural Networks.
Quantitative Propagation of Chaos for SGD in Wide Neural Networks.
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach.
The Statistical Complexity of Early-Stopped Mirror Descent.
Stein Self-Repulsive Dynamics: Benefits From Past Samples.
Statistical Guarantees of Distributed Nearest Neighbor Classification.
Reciprocal Adversarial Learning via Characteristic Functions.
Deep reconstruction of strange attractors from time series.
Permute-and-Flip: A new mechanism for differentially private selection.
Improving Local Identifiability in Probabilistic Box Embeddings.
Cascaded Text Generation with Markov Transformers.
Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering.
Adversarially Robust Streaming Algorithms via Differential Privacy.
Synbols: Probing Learning Algorithms with Synthetic Datasets.
Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds.
Fourier Sparse Leverage Scores and Approximate Kernel Learning.
PyGlove: Symbolic Programming for Automated Machine Learning.
Backpropagating Linearly Improves Transferability of Adversarial Examples.
Fast and Flexible Temporal Point Processes with Triangular Maps.
Neural Methods for Point-wise Dependency Estimation.
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift.
Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method.
Self-Supervised MultiModal Versatile Networks.
An Unsupervised Information-Theoretic Perceptual Quality Metric.
A graph similarity for deep learning.
