icml 2021 论文列表
Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event.
|
A Functional Perspective on Learning Symmetric Functions with Neural Networks.
On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients.
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise.
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning.
Contrastive Learning Inverts the Data Generating Process.
Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning.
Recovering AES Keys with a Deep Cold Boot Attack.
Demystifying Inductive Biases for (Beta-)VAE Based Architectures.
Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks.
Commutative Lie Group VAE for Disentanglement Learning.
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels.
Few-shot Language Coordination by Modeling Theory of Mind.
Spectral vertex sparsifiers and pair-wise spanners over distributed graphs.
Data-Free Knowledge Distillation for Heterogeneous Federated Learning.
Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm.
Examining and Combating Spurious Features under Distribution Shift.
Asymmetric Loss Functions for Learning with Noisy Labels.
Towards Defending against Adversarial Examples via Attack-Invariant Features.
Incentivized Bandit Learning with Self-Reinforcing User Preferences.
Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations.
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation.
Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping.
Towards Distraction-Robust Active Visual Tracking.
Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions.
How Framelets Enhance Graph Neural Networks.
Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination.
Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation.
Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial Attacks.
Few-Shot Neural Architecture Search.
Calibrate Before Use: Improving Few-shot Performance of Language Models.
Joining datasets via data augmentation in the label space for neural networks.
Dataset Condensation with Differentiable Siamese Augmentation.
Learning to Rehearse in Long Sequence Memorization.
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity.
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation.
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference.
Breaking the Deadly Triad with a Target Network.
World Model as a Graph: Learning Latent Landmarks for Planning.
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration.
Matrix Sketching for Secure Collaborative Machine Learning.
Average-Reward Off-Policy Policy Evaluation with Function Approximation.
Deep Coherent Exploration for Continuous Control.
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients.
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution.
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion.
Towards Better Robust Generalization with Shift Consistency Regularization.
Quantile Bandits for Best Arms Identification.
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization.
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning.
Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation.
Learning from Noisy Labels with No Change to the Training Process.
PAPRIKA: Private Online False Discovery Rate Control.
Probabilistic Generating Circuits.
Poolingformer: Long Document Modeling with Pooling Attention.
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models.
Bayesian Attention Belief Networks.
Near Optimal Reward-Free Reinforcement Learning.
Robust Policy Gradient against Strong Data Corruption.
Efficient Lottery Ticket Finding: Less Data is More.
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons.
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
DORO: Distributional and Outlier Robust Optimization.
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning.
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling.
Barlow Twins: Self-Supervised Learning via Redundancy Reduction.
Learning Binary Decision Trees by Argmin Differentiation.
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL.
Grey-box Extraction of Natural Language Models.
Three Operator Splitting with a Nonconvex Loss Function.
Federated Composite Optimization.
On Explainability of Graph Neural Networks via Subgraph Explorations.
Neural Tangent Generalization Attacks.
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity.
Large Scale Private Learning via Low-rank Reparametrization.
Learning Generalized Intersection Over Union for Dense Pixelwise Prediction.
Deep Latent Graph Matching.
Whittle Networks: A Deep Likelihood Model for Time Series.
Provably Efficient Algorithms for Multi-Objective Competitive RL.
DAGs with No Curl: An Efficient DAG Structure Learning Approach.
Exponentially Many Local Minima in Quantum Neural Networks.
LogME: Practical Assessment of Pre-trained Models for Transfer Learning.
Graph Contrastive Learning Automated.
Lower-Bounded Proper Losses for Weakly Supervised Classification.
Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm.
Autoencoding Under Normalization Constraints.
Federated Continual Learning with Weighted Inter-client Transfer.
Adversarial Purification with Score-based Generative Models.
Conditional Temporal Neural Processes with Covariance Loss.
SinIR: Efficient General Image Manipulation with Single Image Reconstruction.
Path Planning using Neural A* Search.
Distributed Nyström Kernel Learning with Communications.
Continuous-time Model-based Reinforcement Learning.
Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints.
Improved OOD Generalization via Adversarial Training and Pretraing.
From Local Structures to Size Generalization in Graph Neural Networks.
Neighborhood Contrastive Learning Applied to Online Patient Monitoring.
Improving Gradient Regularization using Complex-Valued Neural Networks.
Break-It-Fix-It: Unsupervised Learning for Program Repair.
Elementary superexpressive activations.
Reinforcement Learning with Prototypical Representations.
Addressing Catastrophic Forgetting in Few-Shot Problems.
Deep Learning for Functional Data Analysis with Adaptive Basis Layers.
Improving Generalization in Meta-learning via Task Augmentation.
HAWQ-V3: Dyadic Neural Network Quantization.
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks.
Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks.
Delving into Deep Imbalanced Regression.
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss.
When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC.
Voice2Series: Reprogramming Acoustic Models for Time Series Classification.
Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies.
Representation Matters: Offline Pretraining for Sequential Decision Making.
Graph Neural Networks Inspired by Classical Iterative Algorithms.
Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics.
BASGD: Buffered Asynchronous SGD for Byzantine Learning.
LARNet: Lie Algebra Residual Network for Face Recognition.
Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks.
Learning Optimal Auctions with Correlated Valuations from Samples.
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models.
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection.
On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework.
CATE: Computation-aware Neural Architecture Encoding with Transformers.
Link Prediction with Persistent Homology: An Interactive View.
EL-Attention: Memory Efficient Lossless Attention for Generation.
Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences.
Structured Convolutional Kernel Networks for Airline Crew Scheduling.
KNAS: Green Neural Architecture Search.
Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings.
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth.
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality.
Learner-Private Convex Optimization.
Conformal prediction interval for dynamic time-series.
Self-supervised Graph-level Representation Learning with Local and Global Structure.
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming.
Dash: Semi-Supervised Learning with Dynamic Thresholding.
Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives.
Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold.
To be Robust or to be Fair: Towards Fairness in Adversarial Training.
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee.
Explore Visual Concept Formation for Image Classification.
A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization.
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization.
Learning While Playing in Mean-Field Games: Convergence and Optimality.
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization.
Interaction-Grounded Learning.
Batch Value-function Approximation with Only Realizability.
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity.
RNNRepair: Automatic RNN Repair via Model-based Analysis.
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks.
On the Optimality of Batch Policy Optimization Algorithms.
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty.
Data-efficient Hindsight Off-policy Option Learning.
Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach.
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning.
Generative Video Transformer: Can Objects be the Words?
On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP.
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels.
Temporally Correlated Task Scheduling for Sequence Learning.
ChaCha for Online AutoML.
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning.
Making Paper Reviewing Robust to Bid Manipulation Attacks.
Conjugate Energy-Based Models.
Learning Neural Network Subspaces.
Leveraging Sparse Linear Layers for Debuggable Deep Networks.
Leveraging Language to Learn Program Abstractions and Search Heuristics.
Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations.
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention.
Composing Normalizing Flows for Inverse Problems.
Solving Inverse Problems with a Flow-based Noise Model.
Learning de-identified representations of prosody from raw audio.
Keyframe-Focused Visual Imitation Learning.
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning.
Characterizing the Gap Between Actor-Critic and Policy Gradient.
Leveraged Weighted Loss for Partial Label Learning.
Thinking Like Transformers.
A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting.
Meta-learning Hyperparameter Performance Prediction with Neural Processes.
Inferring serial correlation with dynamic backgrounds.
Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond.
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention.
Robust Asymmetric Learning in POMDPs.
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing.
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation.
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach.
Evolving Attention with Residual Convolutions.
Learning to Weight Imperfect Demonstrations.
Instabilities of Offline RL with Pre-Trained Neural Representation.
UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data.
Matrix Completion with Model-free Weighting.
Quantum algorithms for reinforcement learning with a generative model.
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II.
An exact solver for the Weston-Watkins SVM subproblem.
Directional Bias Amplification.
SketchEmbedNet: Learning Novel Concepts by Imitating Drawings.
Robust Learning for Data Poisoning Attacks.
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks.
ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation.
Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method.
A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network.
Robust Inference for High-Dimensional Linear Models via Residual Randomization.
Deep Generative Learning via Schrödinger Bridge.
SG-PALM: a Fast Physically Interpretable Tensor Graphical Model.
Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time.
AlphaNet: Improved Training of Supernets with Alpha-Divergence.
Label Distribution Learning Machine.
Self-Tuning for Data-Efficient Deep Learning.
Explainable Automated Graph Representation Learning with Hyperparameter Importance.
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework.
Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss.
A Proxy Variable View of Shared Confounding.
Fairness of Exposure in Stochastic Bandits.
Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model.
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces.
Learning and Planning in Average-Reward Markov Decision Processes.
Task-Optimal Exploration in Linear Dynamical Systems.
Safe Reinforcement Learning Using Advantage-Based Intervention.
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization.
Principal Component Hierarchy for Sparse Quadratic Programs.
Object Segmentation Without Labels with Large-Scale Generative Models.
Efficient Training of Robust Decision Trees Against Adversarial Examples.
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization.
Online Graph Dictionary Learning.
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies.
Sparsifying Networks via Subdifferential Inclusion.
Towards Domain-Agnostic Contrastive Learning.
CURI: A Benchmark for Productive Concept Learning Under Uncertainty.
Active Deep Probabilistic Subsampling.
LTL2Action: Generalizing LTL Instructions for Multi-Task RL.
SGLB: Stochastic Gradient Langevin Boosting.
Fast Projection Onto Convex Smooth Constraints.
A Framework for Private Matrix Analysis in Sliding Window Model.
PixelTransformer: Sample Conditioned Signal Generation.
Cumulants of Hawkes Processes are Robust to Observation Noise.
Provable Meta-Learning of Linear Representations.
Learning a Universal Template for Few-shot Dataset Generalization.
A New Formalism, Method and Open Issues for Zero-Shot Coordination.
On Disentangled Representations Learned from Correlated Data.
Bayesian Optimistic Optimisation with Exponentially Decaying Regret.
SMG: A Shuffling Gradient-Based Method with Momentum.
Sparse within Sparse Gaussian Processes using Neighbor Information.
Conservative Objective Models for Effective Offline Model-Based Optimization.
Training data-efficient image transformers & distillation through attention.
Diffusion Earth Mover's Distance and Distribution Embeddings.
Deep Continuous Networks.
Probabilistic Programs with Stochastic Conditioning.
Nonparametric Decomposition of Sparse Tensors.
BORE: Bayesian Optimization by Density-Ratio Estimation.
Online Learning in Unknown Markov Games.
Understanding self-supervised learning dynamics without contrastive pairs.
Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model.
Monte Carlo Variational Auto-Encoders.
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism.
Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers.
Moreau-Yosida f-divergences.
T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP.
OmniNet: Omnidirectional Representations from Transformers.
Synthesizer: Rethinking Self-Attention for Transformer Models.
A Language for Counterfactual Generative Models.
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts.
Understanding the Dynamics of Gradient Flow in Overparameterized Linear models.
REPAINT: Knowledge Transfer in Deep Reinforcement Learning.
Taylor Expansion of Discount Factors.
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed.
SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples.
EfficientNetV2: Smaller Models and Faster Training.
Supervised Tree-Wasserstein Distance.
Approximation Theory Based Methods for RKHS Bandits.
Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training.
DriftSurf: Stable-State / Reactive-State Learning under Concept Drift.
Robust Representation Learning via Perceptual Similarity Metrics.
Parallel tempering on optimized paths.
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap.
Generalization Error Bound for Hyperbolic Ordinal Embedding.
Model-Targeted Poisoning Attacks with Provable Convergence.
Reinforcement Learning for Cost-Aware Markov Decision Processes.
PAC-Learning for Strategic Classification.
Reasoning Over Virtual Knowledge Bases With Open Predicate Relations.
Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition.
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning.
What Makes for End-to-End Object Detection?
AutoSampling: Search for Effective Data Sampling Schedules.
Nondeterminism and Instability in Neural Network Optimization.
Not All Memories are Created Equal: Learning to Forget by Expiring.
More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy Method.
K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets.
Decoupling Representation Learning from Reinforcement Learning.
Decomposed Mutual Information Estimation for Contrastive Representation Learning.
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning.
Oblivious Sketching-based Central Path Method for Linear Programming.
Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums.
Fast Sketching of Polynomial Kernels of Polynomial Degree.
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration.
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving.
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks.
Multi-Task Reinforcement Learning with Context-based Representations.
Skew Orthogonal Convolutions.
Structured World Belief for Reinforcement Learning in POMDP.
Flow-based Attribution in Graphical Models: A Recursive Shapley Approach.
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances.
PopSkipJump: Decision-Based Attack for Probabilistic Classifiers.
Dynamic Planning and Learning under Recovering Rewards.
Collaborative Bayesian Optimization with Fair Regret.
Directed Graph Embeddings in Pseudo-Riemannian Manifolds.
A Precise Performance Analysis of Support Vector Regression.
On Characterizing GAN Convergence Through Proximal Duality Gap.
Testing Group Fairness via Optimal Transport Projections.
Aggregating From Multiple Target-Shifted Sources.
Zoo-Tuning: Adaptive Transfer from A Zoo of Models.
AGENT: A Benchmark for Core Psychological Reasoning.
Large-Scale Meta-Learning with Continual Trajectory Shifting.
GANMEX: One-vs-One Attributions using GAN-based Model Explainability.
Deeply-Debiased Off-Policy Interval Estimation.
Segmenting Hybrid Trajectories using Latent ODEs.
Learning Gradient Fields for Molecular Conformation Generation.
SparseBERT: Rethinking the Importance Analysis in Self-attention.
State Relevance for Off-Policy Evaluation.
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization.
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise.
On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise.
Personalized Federated Learning using Hypernetworks.
Equivariant Networks for Pixelized Spheres.
RRL: Resnet as representation for Reinforcement Learning.
Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems.
State Entropy Maximization with Random Encoders for Efficient Exploration.
Pure Exploration and Regret Minimization in Matching Bandits.
Top-k eXtreme Contextual Bandits with Arm Hierarchy.
Learning Intra-Batch Connections for Deep Metric Learning.
Connecting Sphere Manifolds Hierarchically for Regularization.
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks.
Equivariant message passing for the prediction of tensorial properties and molecular spectra.
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers.
Linear Transformers Are Secretly Fast Weight Programmers.
Low-Rank Sinkhorn Factorization.
A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning.
E(n) Equivariant Graph Neural Networks.
Towards Understanding Learning in Neural Networks with Linear Teachers.
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks.
Meta-Learning Bidirectional Update Rules.
Momentum Residual Neural Networks.
Asymptotics of Ridge Regression in Convolutional Models.
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization.
Dueling Convex Optimization.
Adversarial Dueling Bandits.
Stochastic Sign Descent Methods: New Algorithms and Better Theory.
Unsupervised Part Representation by Flow Capsules.
Training Data Subset Selection for Regression with Controlled Generalization Error.
Model-Based Reinforcement Learning via Latent-Space Collocation.
Simple and Effective VAE Training with Calibrated Decoders.
UnICORNN: A recurrent model for learning very long time dependencies.
Tilting the playing field: Dynamical loss functions for machine learning.
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes.
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding.
An Algorithm for Stochastic and Adversarial Bandits with Switching Costs.
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees.
Multi-group Agnostic PAC Learnability.
Simultaneous Similarity-based Self-Distillation for Deep Metric Learning.
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement.
On the Predictability of Pruning Across Scales.
Discretization Drift in Two-Player Games.
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL.
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data.
On Linear Identifiability of Learned Representations.
Principled Simplicial Neural Networks for Trajectory Prediction.
Best Arm Identification in Graphical Bilinear Bandits.
Solving high-dimensional parabolic PDEs using the tensor train format.
Integrated Defense for Resilient Graph Matching.
Interpreting and Disentangling Feature Components of Various Complexity from DNNs.
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs.
Sharf: Shape-conditioned Radiance Fields from a Single View.
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed.
Align, then memorise: the dynamics of learning with feedback alignment.
Implicit Regularization in Tensor Factorization.
Cross-domain Imitation from Observations.
Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces.
Enhancing Robustness of Neural Networks through Fourier Stabilization.
Generative Particle Variational Inference via Estimation of Functional Gradients.
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting.
MSA Transformer.
End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series.
Zero-Shot Text-to-Image Generation.
Differentially Private Sliced Wasserstein Distance.
Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation Guarantees.
Decoupling Value and Policy for Generalization in Reinforcement Learning.
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning.
A General Framework For Detecting Anomalous Inputs to DNN Classifiers.
Learning Transferable Visual Models From Natural Language Supervision.
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game.
Optimization Planning for 3D ConvNets.
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions.
Neural Transformation Learning for Deep Anomaly Detection Beyond Images.
Budgeted Heterogeneous Treatment Effect Estimation.
Density Constrained Reinforcement Learning.
Oneshot Differentially Private Top-k Selection.
Efficient Differentiable Simulation of Articulated Bodies.
Global Prosody Style Transfer Without Text Transcriptions.
A Probabilistic Approach to Neural Network Pruning.
BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining.
Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset.
Bias-Free Scalable Gaussian Processes via Randomized Truncations.
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech.
GeomCA: Geometric Evaluation of Data Representations.
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs.
Towards Practical Mean Bounds for Small Samples.
Megaverse: Simulating Embodied Agents at One Million Experiences per Second.
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision.
Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders.
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization.
Modelling Behavioural Diversity for Learning in Open-Ended Games.
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length.
Privacy-Preserving Video Classification with Convolutional Neural Networks.
How could Neural Networks understand Programs?
Homomorphic Sensing: Sparsity and Noise.
Ensemble Bootstrapping for Q-Learning.
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints.
PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data.
Optimal Counterfactual Explanations in Tree Ensembles.
Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation.
Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression.
Unsupervised Representation Learning via Neural Activation Coding.
Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data.
Leveraging Good Representations in Linear Contextual Bandits.
Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification.
Inference for Network Regression Models with Community Structure.
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting.
Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics.
Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling.
Vector Quantized Models for Planning.
Generalization Guarantees for Neural Architecture Search with Train-Validation Split.
Autoencoder Image Interpolation by Shaping the Latent Space.
Sparsity-Agnostic Lasso Bandit.
Regularizing towards Causal Invariance: Linear Models with Proxies.
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes.
Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods.
Accuracy, Interpretability, and Differential Privacy via Explainable Boosting.
The Impact of Record Linkage on Learning from Feature Partitioned Data.
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points.
Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction.
AdaXpert: Adapting Neural Architecture for Growing Data.
Smooth p-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications.
Improved Denoising Diffusion Probabilistic Models.
Data Augmentation for Meta-Learning.
Differentially Private Densest Subgraph Detection.
Temporal Predictive Coding For Model-Based Planning In Latent Space.
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks.
Nonmyopic Multifidelity Acitve Search.
Interactive Learning from Activity Description.
Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search.
Cross-model Back-translated Distillation for Unsupervised Machine Translation.
Value-at-Risk Optimization with Gaussian Processes.
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths.
Incentivizing Compliance with Algorithmic Instruments.
Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners.
Policy Caches with Successor Features.
Continuous Coordination As a Realistic Scenario for Lifelong Learning.
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information.
Emergent Social Learning via Multi-agent Reinforcement Learning.
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search.
Geometric convergence of elliptical slice sampling.
Generating images with sparse representations.
Randomized Dimensionality Reduction for Facility Location and Single-Linkage Clustering.
Memory-Efficient Pipeline-Parallel DNN Training.
GMAC: A Distributional Perspective on Actor-Critic Framework.
Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding.
Online Limited Memory Neural-Linear Bandits with Likelihood Matching.
No-regret Algorithms for Capturing Events in Poisson Point Processes.
Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold.
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning.
Oblivious Sketching for Logistic Regression.
Outlier-Robust Optimal Transport.
Connecting Interpretability and Robustness in Decision Trees through Separation.
Neural Rough Differential Equations for Long Time Series.
Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games.
PODS: Policy Optimization via Differentiable Simulation.
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization.
Offline Meta-Reinforcement Learning with Advantage Weighting.
An Identifiable Double VAE For Disentangled Representations.
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks.
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation.
Signatured Deep Fictitious Play for Mean Field Games with Common Noise.
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization.
Outside the Echo Chamber: Optimizing the Performative Risk.
EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture.
Learning in Nonzero-Sum Stochastic Games with Potentials.
Mixed Nash Equilibria in the Adversarial Examples Game.
Provably Efficient Learning of Transferable Rewards.
Counterfactual Credit Assignment in Model-Free Reinforcement Learning.
Learn2Hop: Learned Optimization on Rough Landscapes.
A statistical perspective on distillation.
An Integer Linear Programming Framework for Mining Constraints from Data.
UCB Momentum Q-learning: Correcting the bias without forgetting.
Fast active learning for pure exploration in reinforcement learning.
Neural Architecture Search without Training.
A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions.
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks.
Leveraging Non-uniformity in First-order Non-convex Optimization.
Fundamental Tradeoffs in Distributionally Adversarial Training.
Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees.
Robust Unsupervised Learning via L-statistic Minimization.
Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction.
Necessary and sufficient conditions for causal feature selection in time series with latent common causes.
Blind Pareto Fairness and Subgroup Robustness.
Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers.
Explanations for Monotonic Classifiers.
Adaptive Sampling for Best Policy Identification in Markov Decision Processes.
Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs.
Consistent Nonparametric Methods for Network Assisted Covariate Estimation.
Beyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental Design.
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity.
A Sampling-Based Method for Tensor Ring Decomposition.
Inverse Constrained Reinforcement Learning.
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels.
KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning.
Near-Optimal Algorithms for Explainable k-Medians and k-Means.
Exploiting structured data for learning contagious diseases under incomplete testing.
Nonparametric Hamiltonian Monte Carlo.
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness.
Domain Generalization using Causal Matching.
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning.
Learning Interaction Kernels for Agent Systems on Riemannian Manifolds.
Learning to Generate Noise for Multi-Attack Robustness.
Local Algorithms for Finding Densely Connected Clusters.
Learning Stochastic Behaviour from Aggregate Data.
Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface.
Meta-Cal: Well-controlled Post-hoc Calibration by Ranking.
Value Iteration in Continuous Actions, States and Time.
HyperHyperNetwork for the Design of Antenna Arrays.
Trajectory Diversity for Zero-Shot Coordination.
GraphDF: A Discrete Flow Model for Molecular Graph Generation.
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.
On Monotonic Linear Interpolation of Neural Network Parameters.
ACE: Explaining cluster from an adversarial perspective.
Variance Reduced Training with Stratified Sampling for Forecasting Models.
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification.
DANCE: Enhancing saliency maps using decoys.
Optimal Complexity in Decentralized Training.
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture.
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach.
Joint Online Learning and Decision-making via Dual Mirror Descent.
Relative Positional Encoding for Transformers with Linear Complexity.
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning.
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent.
Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport.
Group Fisher Pruning for Practical Network Compression.
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play.
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training.
Watermarking Deep Neural Networks with Greedy Residuals.
Leveraging Public Data for Practical Private Query Release.
Learning Deep Neural Networks under Agnostic Corrupted Supervision.
SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis.
How Do Adam and Training Strategies Help BNNs Optimization.
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices.
On Robust Mean Estimation under Coordinate-level Corruption.
Temporal Difference Learning as Gradient Splitting.
Selfish Sparse RNN Training.
A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization.
From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments.
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition.
One Pass Late Fusion Multi-view Clustering.
Elastic Graph Neural Networks.
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning.
Stochastic Iterative Graph Matching.
Heterogeneous Risk Minimization.
Event Outlier Detection in Continuous Time.
Just Train Twice: Improving Group Robustness without Training Group Information.
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks.
Dynamic Game Theoretic Neural Optimizer.
Learning by Turning: Neural Architecture Aware Optimisation.
APS: Active Pretraining with Successor Features.
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments.
The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression.
Phase Transitions, Distance Functions, and Implicit Neural Representations.
Active Learning of Continuous-time Bayesian Networks through Interventions.
Tractable structured natural-gradient descent using local parameterizations.
Generative Causal Explanations for Graph Neural Networks.
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data.
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation.
Making transport more robust and interpretable by moving data through a small number of anchor points.
Debiasing a First-order Heuristic for Approximate Bi-level Optimization.
Guided Exploration with Proximal Policy Optimization using a Single Demonstration.
Information Obfuscation of Graph Neural Networks.
Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement Learning.
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability.
Towards Understanding and Mitigating Social Biases in Language Models.
A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance.
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models.
Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator.
Online Unrelated Machine Load Balancing with Predictions Revisited.
FILTRA: Rethinking Steerable CNN by Filter Transform.
Communication-Efficient Distributed SVD via Local Power Iterations.
Distributionally Robust Optimization with Markovian Data.
The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks.
Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions.
Partially Observed Exchangeable Modeling.
Active Feature Acquisition with Generative Surrogate Models.
Training Graph Neural Networks with 1000 Layers.
Mixed Cross Entropy Loss for Neural Machine Translation.
A Novel Method to Solve Neural Knapsack Problems.
Provably End-to-end Label-noise Learning without Anchor Points.
Sharper Generalization Bounds for Clustering.
Approximate Group Fairness for Clustering.
Quantization Algorithms for Random Fourier Features.
Ditto: Fair and Robust Federated Learning Through Personalization.
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning.
Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph.
Privacy-Preserving Feature Selection with Secure Multiparty Computation.
A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration.
Winograd Algorithm for AdderNet.
Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning.
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization.
Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models.
BASE Layers: Simplifying Training of Large, Sparse Models.
Improved, Deterministic Smoothing for L1 Certified Robustness.
Strategic Classification Made Practical.
SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data.
Learning to Price Against a Moving Target.
Globally-Robust Neural Networks.
Better Training using Weight-Constrained Stochastic Dynamics.
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot.
Stability and Generalization of Stochastic Gradient Methods for Minimax Problems.
Near-Optimal Linear Regression under Distribution Shift.
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training.
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously.
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning.
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation.
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity.
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification.
On-the-fly Rectification for Robust Large-Vocabulary Topic Inference.
Fair Selective Classification Via Sufficiency.
Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer.
Gaussian Process-Based Real-Time Learning for Safety Critical Applications.
LAMDA: Label Matching Deep Domain Adaptation.
Improved Regret Bound and Experience Replay in Regularized Policy Iteration.
MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space.
CountSketches, Feature Hashing and the Median of Three.
Efficient Message Passing for 0-1 ILPs with Binary Decision Diagrams.
Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch).
Discovering symbolic policies with deep reinforcement learning.
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions.
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix.
Model Fusion for Personalized Learning.
Generalization Bounds in the Presence of Outliers: a Median-of-Means Study.
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality.
On the price of explainability for some clustering problems.
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks.
Targeted Data Acquisition for Evolving Negotiation Agents.
Meta-Thompson Sampling.
A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples.
Implicit rate-constrained optimization of non-decomposable objectives.
Bayesian Structural Adaptation for Continual Learning.
Differentially Private Bayesian Inference for Generalized Linear Models.
Near-Optimal Confidence Sequences for Bounded Random Variables.
Out-of-Distribution Generalization via Risk Extrapolation (REx).
Adapting to misspecification in contextual bandits with offline regression oracles.
Revisiting Peng's Q(λ) for Modern Reinforcement Learning.
ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks.
Offline Reinforcement Learning with Fisher Divergence Critic Regularization.
High Confidence Generalization for Reinforcement Learning.
Active Testing: Sample-Efficient Model Evaluation.
NeRF-VAE: A Geometry Aware 3D Scene Generative Model.
Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size.
Kernel Stein Discrepancy Descent.
Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
A Distribution-dependent Analysis of Meta Learning.
Consensus Control for Decentralized Deep Learning.
A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning.
One-sided Frank-Wolfe algorithms for saddle problems.
WILDS: A Benchmark of in-the-Wild Distribution Shifts.
Representational aspects of depth and conditioning in normalizing flows.
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More.
CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients.
Bias-Robust Bayesian Optimization via Dueling Bandits.
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision.
Unsupervised Skill Discovery with Bottleneck Option Learning.
The Lipschitz Constant of Self-Attention.
Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations.
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning.
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech.
Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning.
I-BERT: Integer-only BERT Quantization.
Reward Identification in Inverse Reinforcement Learning.
Self-Improved Retrosynthetic Planning.
Improving Predictors via Combination Across Diverse Task Categories.
GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training.
Neural SDEs as Infinite-Dimensional GANs.
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms.
Functional Space Analysis of Local GAN Convergence.
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm.
Markpainting: Adversarial Machine Learning meets Inpainting.
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets.
Interpretable Stability Bounds for Spectral Graph Filters.
Self Normalizing Flows.
Prior Image-Constrained Reconstruction using Style-Based Generative Models.
Regularized Submodular Maximization at Scale.
When Does Data Augmentation Help With Membership Inference Attacks?
Improved Algorithms for Agnostic Pool-based Active Classification.
Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation.
Learning from History for Byzantine Robust Optimization.
Off-Policy Confidence Sequences.
Variational Auto-Regressive Gaussian Processes for Continual Learning.
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes.
Statistical Estimation from Dependent Data.
Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations.
Optimal Off-Policy Evaluation from Multiple Logging Policies.
Projection techniques to update the truncated SVD of evolving matrices with applications.
A Differentiable Point Process with Its Application to Spiking Neural Networks.
Practical and Private (Deep) Learning Without Sampling or Shuffling.
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation.
Training Recurrent Neural Networks via Forward Propagation Through Time.
A Nullspace Property for Subspace-Preserving Recovery.
Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning.
Detection of Signal in the Spiked Rectangular Models.
Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits.
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models.
Isometric Gaussian Process Latent Variable Model for Dissimilarity Data.
Provable Lipschitz Certification for Generative Models.
Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information.
Adversarial Option-Aware Hierarchical Imitation Learning.
Is Pessimism Provably Efficient for Offline RL?
MOTS: Minimax Optimal Thompson Sampling.
Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits.
Towards Tight Bounds on the Sample Complexity of Average-reward MDPs.
Optimal Streaming Algorithms for Multi-Armed Bandits.
Characterizing Structural Regularities of Labeled Data in Overparameterized Models.
Emphatic Algorithms for Deep Reinforcement Learning.
Active Covering.
Online Selection Problems against Constrained Adversary.
The Emergence of Individuality.
Single Pass Entrywise-Transformed Low Rank Approximation.
Streaming and Distributed Algorithms for Robust Column Subset Selection.
Approximation Theory of Convolutional Architectures for Time Series Modelling.
Monotonic Robust Policy Optimization with Model Discrepancy.
Prioritized Level Replay.
Self-Damaging Contrastive Learning.
Multi-Dimensional Classification via Sparse Label Encoding.
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision.
Efficient Statistical Tests: A Neural Tangent Kernel Approach.
Bilevel Optimization: Convergence Analysis and Enhanced Design.
Marginalized Stochastic Natural Gradients for Black-Box Variational Inference.
Fast margin maximization via dual acceleration.
Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction.
DeepReDuce: ReLU Reduction for Fast Private Inference.
Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding.
Objective Bound Conditional Gaussian Process for Bayesian Optimization.
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics.
In-Database Regression in Input Sparsity Time.
Policy Gradient Bayesian Robust Optimization for Imitation Learning.
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization.
Inverse Decision Modeling: Learning Interpretable Representations of Behavior.
Improved Regret Bounds of Bilinear Bandits using Action Space Analysis.
Feature Clustering for Support Identification in Extreme Regions.
Fairness for Image Generation with Uncertain Sensitive Attributes.
Instance-Optimal Compressed Sensing via Posterior Sampling.
Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free.
Alternative Microfoundations for Strategic Classification.
Local Correlation Clustering with Asymmetric Classification Errors.
Imitation by Predicting Observations.
Perceiver: General Perception with Iterative Attention.
How to Learn when Data Reacts to Your Model: Performative Gradient Descent.
What Are Bayesian Neural Network Posteriors Really Like?
Distributed Second Order Methods with Fast Rates and Compressed Communication.
Randomized Exploration in Reinforcement Learning with General Value Function Approximation.
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning.
Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization.
Active Learning for Distributionally Robust Level-Set Estimation.
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning.
Selecting Data Augmentation for Simulating Interventions.
Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization.
LieTransformer: Equivariant Self-Attention for Lie Groups.
Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions.
Hyperparameter Selection for Imitation Learning.
Neural Pharmacodynamic State Space Modeling.
Generative Adversarial Transformers.
Learning and Planning in Complex Action Spaces.
Accurate Post Training Quantization With Small Calibration Sets.
Projection Robust Wasserstein Barycenters.
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance.
STRODE: Stochastic Boundary Ordinary Differential Equation.
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis.
A Novel Sequential Coreset Method for Gradient Descent Algorithms.
On Recovering from Modeling Errors Using Testing Bayesian Networks.
A Scalable Deterministic Global Optimization Algorithm for Clustering Problems.
Generalizable Episodic Memory for Deep Reinforcement Learning.
Off-Belief Learning.
On the Random Conjugate Kernel and Neural Tangent Kernel.
Near-Optimal Representation Learning for Linear Bandits and Linear RL.
The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets.
Federated Learning of User Verification Models Without Sharing Embeddings.
Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication.
Latent Programmer: Discrete Latent Codes for Program Synthesis.
Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes.
Learning Curves for Analysis of Deep Networks.
MC-LSTM: Mass-Conserving LSTM.
Multiplicative Noise and Heavy Tails in Stochastic Optimization.
Trees with Attention for Set Prediction Tasks.
Optimizing Black-box Metrics with Iterative Example Weighting.
Learning Representations by Humans, for Humans.
Muesli: Combining Improvements in Policy Optimization.
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity.
Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging.
Finding Relevant Information via a Discrete Fourier Expansion.
Logarithmic Regret for Reinforcement Learning with Linear Function Approximation.
SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform.
PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models.
Boosting for Online Convex Optimization.
Defense against backdoor attacks via robust covariance estimation.
Hierarchical VAEs Know What They Don't Know.
Model Performance Scaling with Multiple Data Sources.
Valid Causal Inference with (Some) Invalid Instruments.
Compressed Maximum Likelihood.
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference.
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient.
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning.
A Collective Learning Framework to Boost GNN Expressiveness for Node Classification.
Adversarial Combinatorial Bandits with General Non-linear Reward Functions.
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration.
Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach.
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning.
Adapting to Delays and Data in Adversarial Multi-Armed Bandits.
Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks.
The Heavy-Tail Phenomenon in SGD.
Correcting Exposure Bias for Link Recommendation.
Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting.
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning.
Soft then Hard: Rethinking the Quantization in Neural Image Compression.
Adversarial Policy Learning in Two-player Competitive Games.
Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games.
On a Combination of Alternating Minimization and Nesterov's Momentum.
Operationalizing Complex Causes: A Pragmatic View of Mediation.
AutoAttend: Automated Attention Representation Search.
Crystallization Learning with the Delaunay Triangulation.
Detecting Rewards Deterioration in Episodic Reinforcement Learning.
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions.
Dissecting Supervised Constrastive Learning.
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline.
Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures.
MARINA: Faster Non-Convex Distributed Learning with Compression.
On the Problem of Underranking in Group-Fair Ranking.
Active Slices for Sliced Stein Discrepancy.
Function Contrastive Learning of Transferable Meta-Representations.
12-Lead ECG Reconstruction via Koopman Operators.
Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective.
Query Complexity of Adversarial Attacks.
Differentially Private Quantiles.
The Power of Adaptivity for Stochastic Submodular Cover.
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message.
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL.
Strategic Classification in the Dark.
How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference.
On the difficulty of unbiased alpha divergence minimization.
Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework.
Parametric Graph for Unimodal Ranking Bandit.
What does LIME really see in images?
On Proximal Policy Optimization's Heavy-tailed Gradients.
RATT: Leveraging Unlabeled Data to Guarantee Generalization.
Discriminative Complementary-Label Learning with Weighted Loss.
Unsupervised Co-part Segmentation through Assembly.
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks.
An Information-Geometric Distance on the Space of Tasks.
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning.
Learning disentangled representations via product manifold projection.
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation.
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators.
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference.
Learning Task Informed Abstractions.
Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing.
Bayesian Quadrature on Riemannian Data Manifolds.
Variational Data Assimilation with a Learned Inverse Observation Operator.
Post-selection inference with HSIC-Lasso.
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise.
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins.
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning.
Efficient Online Learning for Dynamic k-Clustering.
Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design.
Online A-Optimal Design and Active Linear Regression.
Online Learning with Optimism and Delay.
What's in the Box? Exploring the Inner Life of Neural Networks with Robust Rules.
Scalable Certified Segmentation via Randomized Smoothing.
Few-Shot Conformal Prediction with Auxiliary Tasks.
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups.
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning.
GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings.
Understanding Noise Injection in GANs.
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation.
Provably Correct Optimization and Exploration with Non-linear Policies.
Pointwise Binary Classification with Pairwise Confidence Comparisons.
Uncertainty Principles of Encoding GANs.
Reserve Price Optimization for First Price Auctions in Display Advertising.
Dimensionality Reduction for the Sum-of-Distances Metric.
Lossless Compression of Efficient Private Local Randomizers.
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach.
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation.
Train simultaneously, generalize better: Stability of gradient-based minimax learners.
Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results.
Near-Optimal Entrywise Anomaly Detection for Low-Rank Matrices with Sub-Exponential Noise.
PID Accelerated Value Iteration Algorithm.
Streaming Bayesian Deep Tensor Factorization.
Learning Bounds for Open-Set Learning.
On Variational Inference in Biclustering Models.
On Estimation in Latent Variable Models.
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies.
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling.
Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks.
Data augmentation for deep learning based accelerated MRI reconstruction with limited data.
Weight-covariance alignment for adversarially robust neural networks.
Cross-Gradient Aggregation for Decentralized Learning from Non-IID Data.
Graph Mixture Density Networks.
Whitening for Self-Supervised Representation Learning.
Revealing the Structure of Deep Neural Networks via Convex Duality.
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs.
Implicit Bias of Linear RNNs.
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations.
Provably Strict Generalisation Benefit for Equivariant Models.
Self-Paced Context Evaluation for Contextual Reinforcement Learning.
Confidence-Budget Matching for Sequential Budgeted Learning.
Reinforcement Learning Under Moral Uncertainty.
Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics.
Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network.
Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning.
Learning Diverse-Structured Networks for Adversarial Robustness.
Estimating α-Rank from A Few Entries with Low Rank Matrix Completion.
Putting the "Learning" into Learning-Augmented Algorithms for Frequency Estimation.
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation.
Improved Contrastive Divergence Training of Energy-Based Models.
Bilinear Classes: A Structural Framework for Provable Generalization in RL.
Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction.
How rotational invariance of common kernels prevents generalization in high dimensions.
Attention is not all you need: pure attention loses rank doubly exponentially with depth.
Kernel-Based Reinforcement Learning: A Finite-Time Analysis.
On Energy-Based Models with Overparametrized Shallow Neural Networks.
Estimation and Quantization of Expected Persistence Diagrams.
Coded-InvNet for Resilient Prediction Serving Systems.
Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach.
XOR-CD: Linearly Convergent Constrained Structure Generation.
ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables.
Context-Aware Online Collective Inference for Templated Graphical Models.
A Wasserstein Minimax Framework for Mixed Linear Regression.
Learning Online Algorithms with Distributional Advice.
Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time.
On the Inherent Regularization Effects of Noise Injection During Training.
Versatile Verification of Tree Ensembles.
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation.
Bayesian Optimization over Hybrid Spaces.
Kernel Continual Learning.
Heterogeneity for the Win: One-Shot Federated Clustering.
Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing.
Toward Better Generalization Bounds with Locally Elastic Stability.
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
Multidimensional Scaling: Approximation and Complexity.
Grid-Functioned Neural Networks.
Transfer-Based Semantic Anomaly Detection.
High-Dimensional Gaussian Process Inference with Derivatives.
Adversarial Robustness Guarantees for Random Deep Neural Networks.
Bayesian Deep Learning via Subnetwork Inference.
Diffusion Source Identification on Networks with Statistical Confidence.
Catformer: Designing Stable Transformers via Sensitivity Analysis.
Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data.
Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers.
Lipschitz normalization for self-attention layers with application to graph neural networks.
SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning.
Measuring Robustness in Deep Learning Based Compressive Sensing.
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models.
BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders.
Newton Method over Networks is Fast up to the Statistical Precision.
Re-understanding Finite-State Representations of Recurrent Policy Networks.
Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation.
Convex Regularization in Monte-Carlo Tree Search.
Sliced Iterative Normalizing Flows.
Fixed-Parameter and Approximation Algorithms for PCA with Outliers.
SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels.
A Tale of Two Efficient and Informative Negative Sampling Distributions.
Offline Reinforcement Learning with Pseudometric Learning.
Consistent regression when oblivious outliers overwhelm.
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases.
Dynamic Balancing for Model Selection in Bandits and RL.
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability.
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning.
ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations.
GBHT: Gradient Boosting Histogram Transform for Density Estimation.
Randomized Algorithms for Submodular Function Maximization with a k-System Constraint.
Parameterless Transductive Feature Re-representation for Few-Shot Learning.
Mind the Box: l1-APGD for Sparse Adversarial Attacks on Image Classifiers.
Environment Inference for Invariant Learning.
Generalised Lipschitz Regularisation Equals Distributional Robustness.
Explaining Time Series Predictions with Dynamic Masks.
Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering.
Characterizing Fairness Over the Set of Good Models Under Selective Labels.
A Discriminative Technique for Multiple-Source Adaptation.
Relative Deviation Margin Bounds.
Fairness and Bias in Online Selection.
Differentiable Particle Filtering via Entropy-Regularized Optimal Transport.
Exploiting Shared Representations for Personalized Federated Learning.
Concentric mixtures of Mallows models for top-k rankings: sampling and identifiability.
Correlation Clustering in Constant Many Parallel Rounds.
Improving Ultrametrics Embeddings Through Coresets.
Differentially-Private Clustering of Easy Instances.
Scaling Properties of Deep Residual Networks.
Riemannian Convex Potential Maps.
Phasic Policy Gradient.
First-Order Methods for Wasserstein Distributionally Robust MDP.
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization.
Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing.
Modeling Hierarchical Structures with Continuous Recursive Neural Networks.
Label-Only Membership Inference Attacks.
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning.
Learning from Nested Data with Ornstein Auto-Encoders.
Unifying Vision-and-Language Tasks via Text Generation.
Robust Learning-Augmented Caching: An Experimental Study.
Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies.
Parallelizing Legendre Memory Unit Training.
Light RUMs.
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates.
Understanding and Mitigating Accuracy Disparity in Regression.
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence.
Problem Dependent View on Structured Thresholding Bandit Problems.
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning.
Self-supervised and Supervised Joint Training for Resource-rich Machine Translation.
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation.
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training.
Accelerating Gossip SGD with Periodic Global Averaging.
A Receptor Skeleton for Capsule Neural Networks.
Cyclically Equivariant Neural Decoders for Cyclic Codes.
Overcoming Catastrophic Forgetting by Bayesian Generative Regularization.
Representation Subspace Distance for Domain Adaptation Regression.
Large-Scale Multi-Agent Deep FBSDEs.
Analysis of stochastic Lanczos quadrature for spectrum approximation.
Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps.
Network Inference and Influence Maximization from Samples.
A Unified Lottery Ticket Hypothesis for Graph Neural Networks.
Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting.
Large-Margin Contrastive Learning with Distance Polarization Regularizer.
SpreadsheetCoder: Formula Prediction from Semi-structured Context.
Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case.
CARTL: Cooperative Adversarially-Robust Transfer Learning.
Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation.
Mandoline: Model Evaluation under Distribution Shift.
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation.
Decentralized Riemannian Gradient Descent on the Stiefel Manifold.
Neural Feature Matching in Implicit 3D Representations.
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks.
Improved Corruption Robust Algorithms for Episodic Reinforcement Learning.
Integer Programming for Causal Structure Learning in the Presence of Latent Variables.
Unsupervised Learning of Visual 3D Keypoints for Control.
Unified Robust Semi-Supervised Variational Autoencoder.
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills.
Classification with Rejection Based on Cost-sensitive Classification.
Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning.
Differentiable Spatial Planning using Transformers.
DeepWalking Backwards: From Embeddings Back to Graphs.
Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection.
Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment.
Locally Private k-Means in One Round.
Goal-Conditioned Reinforcement Learning with Imagined Subgoals.
HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections.
GRAND: Graph Neural Diffusion.
Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks.
Learning Routines for Effective Off-Policy Reinforcement Learning.
Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research.
Best Model Identification: A Rested Bandit Formulation.
Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees.
Disentangling syntax and semantics in the brain with deep networks.
Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data.
Multi-Receiver Online Bayesian Persuasion.
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret.
Optimizing persistent homology based functions.
Parameter-free Locally Accelerated Conditional Gradients.
Learning from Similarity-Confidence Data.
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design.
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections.
A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization.
High-dimensional Experimental Design and Kernel Bandits.
On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization.
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training.
A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization.
Lenient Regret and Good-Action Identification in Gaussian Process Bandits.
A Theory of Label Propagation for Subpopulation Shift.
Finite mixture models do not reliably learn the number of components.
Disambiguation of Weak Supervision leading to Exponential Convergence rates.
Differentially Private Correlation Clustering.
Narrow Margins: Classification, Margins and Fat Tails.
Model-Free and Model-Based Policy Evaluation when Causality is Uncertain.
Value Alignment Verification.
Machine Unlearning for Random Forests.
Reinforcement Learning of Implicit and Explicit Control Flow Instructions.
Evaluating the Implicit Midpoint Integrator for Riemannian Hamiltonian Monte Carlo.
High-Performance Large-Scale Image Recognition Without Normalization.
Offline Contextual Bandits with Overparameterized Models.
The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning.
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks.
Black-box density function estimation using recursive partitioning.
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning.
Multiplying Matrices Without Multiplying.
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision.
Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games.
Scalable Normalizing Flows for Permutation Invariant Densities.
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing.
Neural Symbolic Regression that scales.
Follow-the-Regularized-Leader Routes to Chaos in Routing Games.
TempoRL: Learning When to Act.
Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction.
Finding k in Latent k- polytope.
Sample Complexity of Robust Linear Classification on Separated Data.
Additive Error Guarantees for Weighted Low Rank Approximation.
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries.
Principal Bit Analysis: Autoencoding with Schur-Concave Loss.
Size-Invariant Graph Representations for Graph Classification Extrapolations.
Confidence Scores Make Instance-dependent Label-noise Learning Possible.
Is Space-Time Attention All You Need for Video Understanding?
Learning from Biased Data: A Semi-Parametric Approach.
Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis.
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer.
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling.
Policy Analysis using Synthetic Controls in Continuous-Time.
Directional Graph Networks.
Generalized Doubly Reparameterized Gradient Estimators.
On Limited-Memory Subsampling Strategies for Bandits.
Optimal Thompson Sampling strategies for support-aware CVaR bandits.
Beyond log2(T) regret for decentralized bandits in matching markets.
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming.
Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization.
Approximating a Distribution Using Weight Queries.
Compositional Video Synthesis with Action Graphs.
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models.
Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers.
Regularized Online Allocation Problems: Fairness and Beyond.
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment.
Instance Specific Approximations for Submodular Maximization.
Breaking the Limits of Message Passing Graph Neural Networks.
GLSearch: Maximum Common Subgraph Detection via Learning to Search.
Principled Exploration via Optimistic Bootstrapping and Backward Induction.
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification.
Stabilizing Equilibrium Models by Jacobian Regularization.
How Important is the Train-Validation Split in Meta-Learning?
Locally Adaptive Label Smoothing Improves Predictive Churn.
Skill Discovery for Exploration and Planning using Deep Skill Graphs.
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees.
Faster Kernel Matrix Algebra via Density Estimation.
Uniform Convergence, Adversarial Spheres and a Simple Remedy.
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification.
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent.
Differentially Private Query Release Through Adaptive Projection.
Decomposable Submodular Function Minimization via Maximum Flow.
Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge.
Federated Learning under Arbitrary Communication Patterns.
Dichotomous Optimistic Search to Quantify Human Perception.
Combinatorial Blocking Bandits with Stochastic Delays.
Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry.
Private Adaptive Gradient Methods for Convex Optimization.
Deciding What to Learn: A Rate-Distortion Approach.
Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients.
Dropout: Explicit Forms and Capacity Control.
Analyzing the tree-layer structure of Deep Forests.
Permutation Weighting.
Annealed Flow Transport Monte Carlo.
The Logical Options Framework.
Unitary Branching Programs: Learnability and Lower Bounds.
Preferential Temporal Difference Learning.
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards.
Sparse Bayesian Learning via Stepwise Regression.
Automatic variational inference with cascading flows.
Safe Reinforcement Learning with Linear Function Approximation.
Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity.
Dataset Dynamics via Gradient Flows in Probability Space.
Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions.
Communication-Efficient Distributed Optimization with Quantized Preconditioners.
Robust Pure Exploration in Linear Bandits with Limited Budget.
A large-scale benchmark for few-shot program induction and synthesis.
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks.
On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting.
How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation.
Deep Kernel Processes.
Label Inference Attacks from Log-loss Scores.
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations.
A Regret Minimization Approach to Iterative Learning Control.
Acceleration via Fractal Learning Rate Schedules.
Towards Rigorous Interpretations: a Formalisation of Feature Attribution.
f-Domain Adversarial Learning: Theory and Algorithms.
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning.
Robust Testing and Estimation under Manipulation Attacks.
Memory Efficient Online Meta Learning.
Debiasing Model Updates for Improving Personalized Federated Training.
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling.
A New Representation of Successor Features for Transfer across Dissimilar Environments.
