icml 2018 论文列表
Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018.
|
Hierarchical Long-term Video Prediction without Supervision.
Stochastic Variance-Reduced Hamilton Monte Carlo Methods.
Message Passing Stein Variational Gradient Descent.
Distributed Nonparametric Regression under Communication Constraints.
Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors.
Stochastic Variance-Reduced Cubic Regularized Newton Method.
A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates.
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?
Understanding Generalization and Optimization Performance of Deep CNNs.
Revealing Common Statistical Behaviors in Heterogeneous Populations.
A Robust Approach to Sequential Information Theoretic Planning.
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data.
Composite Marginal Likelihood Methods for Random Utility Models.
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning.
Adversarially Regularized Autoencoders.
Inter and Intra Topic Structure Learning with Word Embeddings.
Dynamic Regret of Strongly Adaptive Methods.
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents.
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery.
Noisy Natural Gradient as Variational Inference.
Composable Planning with Attributes.
Deep Bayesian Nonparametric Tracking.
Tropical Geometry of Deep Neural Networks.
Learning Long Term Dependencies via Fourier Recurrent Units.
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization.
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms.
Safe Element Screening for Submodular Function Minimization.
High Performance Zero-Memory Overhead Direct Convolutions.
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion.
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow.
Policy Optimization as Wasserstein Gradient Flows.
Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs.
Orthogonal Machine Learning: Power and Limitations.
A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming.
An Efficient Semismooth Newton Based Algorithm for Convex Clustering.
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models.
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks.
GAIN: Missing Data Imputation using Generative Adversarial Nets.
Probably Approximately Metric-Fair Learning.
Disentangled Sequential Autoencoder.
Semi-Implicit Variational Inference.
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates.
Loss Decomposition for Fast Learning in Large Output Spaces.
Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach.
Communication-Computation Efficient Gradient Coding.
Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under ?p Distances.
Hierarchical Text Generation and Planning for Strategic Dialogue.
Yes, but Did It Work?: Evaluating Variational Inference.
Mean Field Multi-Agent Reinforcement Learning.
Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy.
Dependent Relational Gamma Process Models for Longitudinal Networks.
Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions.
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics.
Active Learning with Logged Data.
Causal Bandits with Propagating Inference.
A Semantic Loss Function for Deep Learning with Symbolic Knowledge.
Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions.
Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data.
Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information.
Learning to Explore via Meta-Policy Gradient.
Representation Learning on Graphs with Jumping Knowledge Networks.
Learning Registered Point Processes from Idiosyncratic Observations.
Rates of Convergence of Spectral Methods for Graphon Estimation.
Learning Semantic Representations for Unsupervised Domain Adaptation.
Nonoverlap-Promoting Variable Selection.
Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis.
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks.
Model-Level Dual Learning.
Bayesian Quadrature for Multiple Related Integrals.
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions.
Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization.
Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms.
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training.
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization.
SQL-Rank: A Listwise Approach to Collaborative Ranking.
Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits.
Local Density Estimation in High Dimensions.
Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope.
Towards Fast Computation of Certified Robustness for ReLU Networks.
Deep Predictive Coding Network for Object Recognition.
LEAPSANDBOUNDS: A Method for Approximately Optimal Algorithm Configuration.
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples.
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks.
Hierarchical Multi-Label Classification Networks.
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions.
Stein Variational Message Passing for Continuous Graphical Models.
Online Convolutional Sparse Coding with Sample-Dependent Dictionary.
Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Convariates.
Adversarial Distillation of Bayesian Neural Network Posteriors.
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis.
Provable Variable Selection for Streaming Features.
A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models.
Coded Sparse Matrix Multiplication.
Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations.
Analyzing the Robustness of Nearest Neighbors to Adversarial Examples.
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning.
Thompson Sampling for Combinatorial Semi-Bandits.
Neural Dynamic Programming for Musical Self Similarity.
Semi-Supervised Learning on Data Streams via Temporal Label Propagation.
Transfer Learning via Learning to Transfer.
A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization.
Programmatically Interpretable Reinforcement Learning.
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations.
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks.
The Mirage of Action-Dependent Baselines in Reinforcement Learning.
Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator.
Invariance of Weight Distributions in Rectified MLPs.
StrassenNets: Deep Learning with a Multiplication Budget.
Theoretical Analysis of Sparse Subspace Clustering with Missing Entries.
Learning Longer-term Dependencies in RNNs with Auxiliary Losses.
Convergent TREE BACKUP and RETRACE with Function Approximation.
Adversarial Regression with Multiple Learners.
Importance Weighted Transfer of Samples in Reinforcement Learning.
CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions.
Decoupling Gradient-Like Learning Rules from Representations.
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks.
Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees.
Chi-square Generative Adversarial Network.
Best Arm Identification in Linear Bandits with Linear Dimension Dependency.
Black Box FDR.
Neural Inverse Rendering for General Reflectance Photometric Stereo.
D2: Decentralized Training over Decentralized Data.
Learning the Reward Function for a Misspecified Model.
Differentiable Compositional Kernel Learning for Gaussian Processes.
Convolutional Imputation of Matrix Networks.
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation.
Scalable Approximate Bayesian Inference for Particle Tracking Data.
Neural Program Synthesis from Diverse Demonstration Videos.
Stagewise Safe Bayesian Optimization with Gaussian Processes.
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search.
Learning Low-Dimensional Temporal Representations.
Approximation Algorithms for Cascading Prediction Models.
Structured Control Nets for Deep Reinforcement Learning.
Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control.
Knowledge Transfer with Jacobian Matching.
Accelerating Natural Gradient with Higher-Order Invariance.
An Inference-Based Policy Gradient Method for Learning Options.
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron.
K-means clustering using random matrix sparsification.
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization.
CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning.
TACO: Learning Task Decomposition via Temporal Alignment for Control.
A Spectral Approach to Gradient Estimation for Implicit Distributions.
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method.
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication.
Learning in Integer Latent Variable Models with Nested Automatic Differentiation.
Locally Private Hypothesis Testing.
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost.
Solving Partial Assignment Problems using Random Clique Complexes.
Finding Influential Training Samples for Gradient Boosted Decision Trees.
First Order Generative Adversarial Networks.
Bounding and Counting Linear Regions of Deep Neural Networks.
Overcoming Catastrophic Forgetting with Hard Attention to the Task.
Multi-Fidelity Black-Box Optimization with Hierarchical Partitions.
Progress & Compress: A scalable framework for continual learning.
Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care.
Learning with Abandonment.
Tight Regret Bounds for Bayesian Optimization in One Dimension.
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service.
A Classification-Based Study of Covariate Shift in GAN Distributions.
Measuring abstract reasoning in neural networks.
Graph Networks as Learnable Physics Engines for Inference and Control.
Representation Tradeoffs for Hyperbolic Embeddings.
Tempered Adversarial Networks.
Learning Equations for Extrapolation and Control.
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks.
Black-Box Variational Inference for Stochastic Differential Equations.
Probabilistic Boolean Tensor Decomposition.
Augment and Reduce: Stochastic Inference for Large Categorical Distributions.
Deep One-Class Classification.
Fast Information-theoretic Bayesian Optimisation.
Learning to Optimize Combinatorial Functions.
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music.
Been There, Done That: Meta-Learning with Episodic Recall.
Learning by Playing Solving Sparse Reward Tasks from Scratch.
Learning to Reweight Examples for Robust Deep Learning.
Weightless: Lossy weight encoding for deep neural network compression.
Learning Implicit Generative Models with the Method of Learned Moments.
Gradient Coding from Cyclic MDS Codes and Expander Graphs.
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate.
Tighter Variational Bounds are Not Necessarily Better.
On Nesting Monte Carlo Estimators.
Modeling Others using Oneself in Multi-Agent Reinforcement Learning.
Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation.
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Fast Parametric Learning with Activation Memorization.
Machine Theory of Mind.
Non-convex Conditional Gradient Sliding.
DCFNet: Deep Neural Network with Decomposed Convolutional Filters.
Gradually Updated Neural Networks for Large-Scale Image Recognition.
Do Outliers Ruin Collaboration?
Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction.
Selecting Representative Examples for Program Synthesis.
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets.
Learning Dynamics of Linear Denoising Autoencoders.
Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory.
Local Convergence Properties of SAGA/Prox-SVRG and Acceleration.
Constant-Time Predictive Distributions for Gaussian Processes.
Bandits with Delayed, Aggregated Anonymous Feedback.
Efficient Neural Architecture Search via Parameter Sharing.
Adaptive Three Operator Splitting.
High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach.
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos.
Image Transformer.
Time Limits in Reinforcement Learning.
Learning Independent Causal Mechanisms.
Stochastic Variance-Reduced Policy Gradient.
Max-Mahalanobis Linear Discriminant Analysis Networks.
Theoretical Analysis of Image-to-Image Translation with Adversarial Learning.
Learning to Speed Up Structured Output Prediction.
Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control.
Tree Edit Distance Learning via Adaptive Symbol Embeddings.
Learning Compact Neural Networks with Regularization.
Analyzing Uncertainty in Neural Machine Translation.
Efficient First-Order Algorithms for Adaptive Signal Denoising.
Autoregressive Quantile Networks for Generative Modeling.
Learning Localized Spatio-Temporal Models From Streaming Data.
Parallel WaveNet: Fast High-Fidelity Speech Synthesis.
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches.
Transformation Autoregressive Networks.
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks.
Self-Imitation Learning.
BOCK : Bayesian Optimization with Cylindrical Kernels.
Learning in Reproducing Kernel Krein Spaces.
Is Generator Conditioning Causally Related to GAN Performance?
The Uncertainty Bellman Equation and Exploration.
Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams.
Functional Gradient Boosting based on Residual Network Perception.
A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations.
SparseMAP: Differentiable Sparse Structured Inference.
State Space Gaussian Processes with Non-Gaussian Likelihood.
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry.
On Learning Sparsely Used Dictionaries from Incomplete Samples.
Active Testing: An Efficient and Robust Framework for Estimating Accuracy.
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption.
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions.
Optimization Landscape and Expressivity of Deep CNNs.
Mitigating Bias in Adaptive Data Gathering via Differential Privacy.
Stochastic Proximal Algorithms for AUC Maximization.
Nearly Optimal Robust Subspace Tracking.
Smoothed Action Value Functions for Learning Gaussian Policies.
Fitting New Speakers Based on a Short Untranscribed Sample.
On the Relationship between Data Efficiency and Error for Uncertainty Sampling.
Rapid Adaptation with Conditionally Shifted Neurons.
Kernelized Synaptic Weight Matrices.
Dropout Training, Data-dependent Regularization, and Generalization Bounds.
WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models.
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding.
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings.
The Hierarchical Adaptive Forgetting Variational Filter.
Data Summarization at Scale: A Two-Stage Submodular Approach.
A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning.
Differentiable Abstract Interpretation for Provably Robust Neural Networks.
Training Neural Machines with Trace-Based Supervision.
Differentiable plasticity: training plastic neural networks with backpropagation.
One-Shot Segmentation in Clutter.
On the Implicit Bias of Dropout.
Stochastic PCA with ?2 and ?1 Regularization.
The Hidden Vulnerability of Distributed Learning in Byzantium.
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing-and Back.
prDeep: Robust Phase Retrieval with a Flexible Deep Network.
Configurable Markov Decision Processes.
Which Training Methods for GANs do actually Converge?
Ranking Distributions based on Noisy Sorting.
Differentiable Dynamic Programming for Structured Prediction and Attention.
Bounds on the Approximation Power of Feedforward Neural Networks.
Optimization, Fast and Slow: Optimally Switching between Local and Bayesian Optimization.
Bayesian Model Selection for Change Point Detection and Clustering.
Fast Approximate Spectral Clustering for Dynamic Networks.
Streaming Principal Component Analysis in Noisy Settings.
Iterative Amortized Inference.
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning.
Learning Adversarially Fair and Transferable Representations.
Approximate message passing for amplitude based optimization.
Dimensionality-Driven Learning with Noisy Labels.
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion.
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers.
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning.
Celer: a Fast Solver for the Lasso with Dual Extrapolation.
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design.
Competitive Caching with Machine Learned Advice.
End-to-end Active Object Tracking via Reinforcement Learning.
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations.
Structured Variationally Auto-encoded Optimization.
Accelerating Greedy Coordinate Descent Methods.
The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference.
Spectrally Approximating Large Graphs with Smaller Graphs.
Constraining the Dynamics of Deep Probabilistic Models.
Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap.
PDE-Net: Learning PDEs from Data.
On Matching Pursuit and Coordinate Descent.
Fast Stochastic AUC Maximization with O(1/n)-Convergence Rate.
Fast Variance Reduction Method with Stochastic Batch Size.
Open Category Detection with PAC Guarantees.
A Two-Step Computation of the Exact GAN Wasserstein Distance.
Delayed Impact of Fair Machine Learning.
Towards Black-box Iterative Machine Teaching.
Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression.
Detecting and Correcting for Label Shift with Black Box Predictors.
Level-Set Methods for Finite-Sum Constrained Convex Optimization.
Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces.
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods.
Reviving and Improving Recurrent Back-Propagation.
The Dynamics of Learning: A Random Matrix Approach.
On the Spectrum of Random Features Maps of High Dimensional Data.
RLlib: Abstractions for Distributed Reinforcement Learning.
Asynchronous Decentralized Parallel Stochastic Gradient Descent.
Estimation of Markov Chain via Rank-constrained Likelihood.
The Well-Tempered Lasso.
Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering.
On the Limitations of First-Order Approximation in GAN Dynamics.
Towards Binary-Valued Gates for Robust LSTM Training.
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks.
Out-of-sample extension of graph adjacency spectral embedding.
Noise2Noise: Learning Image Restoration without Clean Data.
Deep Asymmetric Multi-task Feature Learning.
Gated Path Planning Networks.
Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling.
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace.
Hierarchical Imitation and Reinforcement Learning.
The Multilinear Structure of ReLU Networks.
Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global.
Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering.
An Estimation and Analysis Framework for the Rasch Model.
Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks.
Canonical Tensor Decomposition for Knowledge Base Completion.
Binary Partitions with Approximate Minimum Impurity.
Mixed batches and symmetric discriminators for GAN training.
Understanding the Loss Surface of Neural Networks for Binary Classification.
Explicit Inductive Bias for Transfer Learning with Convolutional Networks.
Data-Dependent Stability of Stochastic Gradient Descent.
Trainable Calibration Measures For Neural Networks From Kernel Mean Embeddings.
Accurate Uncertainties for Deep Learning Using Calibrated Regression.
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice.
Semiparametric Contextual Bandits.
Dynamic Evaluation of Neural Sequence Models.
Compiling Combinatorial Prediction Games.
On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups.
Nonconvex Optimization for Regression with Fairness Constraints.
Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework.
Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection.
Crowdsourcing with Arbitrary Adversaries.
An Alternative View: When Does SGD Escape Local Minima?
Neural Relational Inference for Interacting Systems.
Semi-Amortized Variational Autoencoders.
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV).
Self-Bounded Prediction Suffix Tree via Approximate String Matching.
Disentangling by Factorising.
Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data.
Blind Justice: Fairness with Encrypted Sensitive Attributes.
Geometry Score: A Method For Comparing Generative Adversarial Networks.
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam.
Convergence guarantees for a class of non-convex and non-smooth optimization problems.
Frank-Wolfe with Subsampling Oracle.
ContextNet: Deep learning for Star Galaxy Classification.
Improved nearest neighbor search using auxiliary information and priority functions.
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness.
Focused Hierarchical RNNs for Conditional Sequence Processing.
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints.
Feasible Arm Identification.
Not All Samples Are Created Equal: Deep Learning with Importance Sampling.
Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis.
LaVAN: Localized and Visible Adversarial Noise.
Continual Reinforcement Learning with Complex Synapses.
Let's be Honest: An Optimal No-Regret Framework for Zero-Sum Games.
Improving Sign Random Projections With Additional Information.
Policy Optimization with Demonstrations.
Semi-Supervised Learning via Compact Latent Space Clustering.
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations.
Residual Unfairness in Fair Machine Learning from Prejudiced Data.
Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit.
Learning Diffusion using Hyperparameters.
Efficient Neural Audio Synthesis.
Kernel Recursive ABC: Point Estimation with Intractable Likelihood.
Fast Decoding in Sequence Models Using Discrete Latent Variables.
Kronecker Recurrent Units.
Composite Functional Gradient Learning of Generative Adversarial Models.
Large-Scale Cox Process Inference using Variational Fourier Features.
WSNet: Compact and Efficient Networks Through Weight Sampling.
Regret Minimization for Partially Observable Deep Reinforcement Learning.
Network Global Testing by Counting Graphlets.
Junction Tree Variational Autoencoder for Molecular Graph Generation.
The Weighted Kendall and High-order Kernels for Permutations.
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels.
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift.
Feedback-Based Tree Search for Reinforcement Learning.
Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks.
Efficient end-to-end learning for quantizable representations.
A Unified Framework for Structured Low-rank Matrix Learning.
Detecting non-causal artifacts in multivariate linear regression models.
Pathwise Derivatives Beyond the Reparameterization Trick.
Video Prediction with Appearance and Motion Conditions.
Differentially Private Matrix Completion Revisited.
Firing Bandits: Optimizing Crowdfunding.
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach.
Anonymous Walk Embeddings.
Unbiased Objective Estimation in Predictive Optimization.
Deep Density Destructors.
Improving Regression Performance with Distributional Losses.
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model.
Black-box Adversarial Attacks with Limited Queries and Information.
Attention-based Deep Multiple Instance Learning.
Deep Variational Reinforcement Learning for POMDPs.
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning.
Decoupled Parallel Backpropagation with Convergence Guarantee.
Topological Mixture Estimation.
Neural Autoregressive Flows.
Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling.
Learning Deep ResNet Blocks Sequentially using Boosting Theory.
Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices.
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs.
Does Distributionally Robust Supervised Learning Give Robust Classifiers?
Variational Bayesian dropout: pitfalls and fixes.
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks.
Sound Abstraction and Decomposition of Probabilistic Programs.
CyCADA: Cycle-Consistent Adversarial Domain Adaptation.
Fast Bellman Updates for Robust MDPs.
Orthogonal Recurrent Neural Networks with Scaled Cayley Transform.
Learning unknown ODE models with Gaussian processes.
Recurrent Predictive State Policy Networks.
Multicalibration: Calibration for the (Computationally-Identifiable) Masses.
Fairness Without Demographics in Repeated Loss Minimization.
Learning Memory Access Patterns.
Deep Models of Interactions Across Sets.
Rectify Heterogeneous Models with Semantic Mapping.
Stein Variational Gradient Descent Without Gradient.
Candidates vs. Noises Estimation for Large Multi-Class Classification Problem.
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning.
Comparison-Based Random Forests.
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.
Latent Space Policies for Hierarchical Reinforcement Learning.
Shampoo: Preconditioned Stochastic Tensor Optimization.
Characterizing Implicit Bias in Terms of Optimization Geometry.
Learning to Search with MCTSnets.
Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines.
Learning Policy Representations in Multiagent Systems.
Visualizing and Understanding Atari Agents.
Learning One Convolutional Layer with Overlapping Patches.
Non-Linear Motor Control by Local Learning in Spiking Neural Networks.
Robust and Scalable Models of Microbiome Dynamics.
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time.
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors.
Linear Spectral Estimators and an Application to Phase Retrieval.
Budgeted Experiment Design for Causal Structure Learning.
The Generalization Error of Dictionary Learning with Moreau Envelopes.
Temporal Poisson Square Root Graphical Models.
Conditional Neural Processes.
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction.
Parallel Bayesian Network Structure Learning.
Spotlight: Optimizing Device Placement for Training Deep Neural Networks.
Synthesizing Programs for Images using Reinforced Adversarial Learning.
Parameterized Algorithms for the Matrix Completion Problem.
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings.
Inductive Two-layer Modeling with Parametric Bregman Transfer.
Local Private Hypothesis Testing: Chi-Square Tests.
Born-Again Neural Networks.
Clipped Action Policy Gradient.
Addressing Function Approximation Error in Actor-Critic Methods.
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning.
Bilevel Programming for Hyperparameter Optimization and Meta-Learning.
ADMM and Accelerated ADMM as Continuous Dynamical Systems.
Generative Temporal Models with Spatial Memory for Partially Observed Environments.
Practical Contextual Bandits with Regression Oracles.
DiCE: The Infinitely Differentiable Monte Carlo Estimator.
Automatic Goal Generation for Reinforcement Learning Agents.
Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization.
Nonparametric variable importance using an augmented neural network with multi-task learning.
Fourier Policy Gradients.
CRVI: Convex Relaxation for Variational Inference.
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.
Efficient and Consistent Adversarial Bipartite Matching.
More Robust Doubly Robust Off-policy Evaluation.
BOHB: Robust and Efficient Hyperparameter Optimization at Scale.
The Limits of Maxing, Ranking, and Preference Learning.
Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF).
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.
Parallel and Streaming Algorithms for K-Core Decomposition.
Beyond the One-Step Greedy Approach in Reinforcement Learning.
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors.
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm.
A Distributed Second-Order Algorithm You Can Trust.
Investigating Human Priors for Playing Video Games.
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima.
On the Power of Over-parametrization in Neural Networks with Quadratic Activation.
Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer.
Essentially No Barriers in Neural Network Energy Landscape.
Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering.
Randomized Block Cubic Newton Method.
Probabilistic Recurrent State-Space Models.
Coordinated Exploration in Concurrent Reinforcement Learning.
Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning.
Noisin: Unbiased Regularization for Recurrent Neural Networks.
Learning to Act in Decentralized Partially Observable MDPs.
Alternating Randomized Block Coordinate Descent.
Modeling Sparse Deviations for Compressed Sensing using Generative Models.
Variational Network Inference: Strong and Stable with Concrete Support.
Accurate Inference for Adaptive Linear Models.
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning.
Stochastic Video Generation with a Learned Prior.
Minibatch Gibbs Sampling on Large Graphical Models.
Escaping Saddles with Stochastic Gradients.
Asynchronous Byzantine Machine Learning (the case of SGD).
Compressing Neural Networks using the Variational Information Bottleneck.
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation.
Adversarial Attack on Graph Structured Data.
Learning Steady-States of Iterative Algorithms over Graphs.
Implicit Quantile Networks for Distributional Reinforcement Learning.
Mix & Match Agent Curricula for Reinforcement Learning.
Inference Suboptimality in Variational Autoencoders.
Constrained Interacting Submodular Groupings.
Online Learning with Abstention.
Efficient ModelBased Deep Reinforcement Learning with Variational State Tabulation.
Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski p-Norms.
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms.
Online Linear Quadratic Control.
On Acceleration with Noise-Corrupted Gradients.
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings.
Stochastic Wasserstein Barycenters.
An Iterative, Sketching-based Framework for Ridge Regression.
Path Consistency Learning in Tsallis Entropy Regularized MDPs.
Structured Evolution with Compact Architectures for Scalable Policy Optimization.
Learning a Mixture of Two Multinomial Logits.
Extreme Learning to Rank via Low Rank Assumption.
Stochastic Training of Graph Convolutional Networks with Variance Reduction.
End-to-End Learning for the Deep Multivariate Probit Model.
Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization.
SADAGRAD: Strongly Adaptive Stochastic Gradient Methods.
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients.
Variational Inference and Model Selection with Generalized Evidence Bounds.
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation.
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks.
PixelSNAIL: An Improved Autoregressive Generative Model.
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations.
Stein Points.
Scalable Bilinear Learning Using State and Action Features.
Continuous-Time Flows for Efficient Inference and Density Estimation.
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity.
Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks.
Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series.
Hierarchical Clustering with Structural Constraints.
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo.
Learning and Memorization.
Stability and Generalization of Learning Algorithms that Converge to Global Optima.
Adversarial Time-to-Event Modeling.
Conditional Noise-Contrastive Estimation of Unnormalised Models.
Fair and Diverse DPP-Based Data Summarization.
Adversarial Learning with Local Coordinate Coding.
Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent.
Improved Large-Scale Graph Learning through Ridge Spectral Sparsification.
Path-Level Network Transformation for Efficient Architecture Search.
Quasi-Monte Carlo Variational Inference.
Predict and Constrain: Modeling Cardinality in Deep Structured Prediction.
Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order.
QuantTree: Histograms for Change Detection in Multivariate Data Streams.
Prediction Rule Reshaping.
A Progressive Batching L-BFGS Method for Machine Learning.
NetGAN: Generating Graphs via Random Walks.
Optimizing the Latent Space of Generative Networks.
Adaptive Sampled Softmax with Kernel Based Sampling.
Autoregressive Convolutional Neural Networks for Asynchronous Time Series.
Distributed Clustering via LSH Based Data Partitioning.
SIGNSGD: Compressed Optimisation for Non-Convex Problems.
Understanding and Simplifying One-Shot Architecture Search.
To Understand Deep Learning We Need to Understand Kernel Learning.
Mutual Information Neural Estimation.
Gradient descent with identity initialization efficiently learns positive definite linear transformations.
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement.
Testing Sparsity over Known and Unknown Bases.
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems.
Geodesic Convolutional Shape Optimization.
Bayesian Optimization of Combinatorial Structures.
Classification from Pairwise Similarity and Unlabeled Data.
Using Inherent Structures to design Lean 2-layer RBMs.
Improved Training of Generative Adversarial Networks using Representative Features.
Improving Optimization in Models With Continuous Symmetry Breaking.
Differentially Private Database Release via Kernel Mean Embeddings.
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients.
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising.
Approximation Guarantees for Adaptive Sampling.
A Spline Theory of Deep Networks.
Spline Filters For End-to-End Deep Learning.
The Mechanics of n-Player Differentiable Games.
Learning to Branch.
A Boo(n) for Evaluating Architecture Performance.
SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions.
Comparing Dynamics: Deep Neural Networks versus Glassy Systems.
Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions.
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing.
Clustering Semi-Random Mixtures of Gaussians.
Synthesizing Robust Adversarial Examples.
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples.
Lipschitz Continuity in Model-based Reinforcement Learning.
Stronger Generalization Bounds for Deep Nets via a Compression Approach.
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization.
Efficient Gradient-Free Variational Inference using Policy Search.
Subspace Embedding and Linear Regression with Orlicz Norm.
MAGAN: Aligning Biological Manifolds.
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory.
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data.
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits.
Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization.
Differentially Private Identity and Equivalence Testing of Discrete Distributions.
Fixing a Broken ELBO.
Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization.
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning.
Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design.
oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis.
Bucket Renormalization for Approximate Inference.
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy.
Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models.
MISSION: Ultra Large-Scale Feature Selection using Count-Sketches.
Accelerated Spectral Ranking.
A Reductions Approach to Fair Classification.
Discovering Interpretable Representations for Both Deep Generative and Discriminative Models.
Learning Representations and Generative Models for 3D Point Clouds.
INSPECTRE: Privately Estimating the Unseen.
Policy and Value Transfer in Lifelong Reinforcement Learning.
State Abstractions for Lifelong Reinforcement Learning.
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems.
