International Conference on Machine Learning (ICML) - 2018

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

$D^2$: Decentralized Training over Decentralized Data 3
A Boo(n) for Evaluating Architecture Performance 2
A Classification-Based Study of Covariate Shift in GAN Distributions 2
A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming 3
A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning 4
A Distributed Second-Order Algorithm You Can Trust 3
A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models 5
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music 3
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery 2
A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization 1
A Progressive Batching L-BFGS Method for Machine Learning 4
A Reductions Approach to Fair Classification 5
A Robust Approach to Sequential Information Theoretic Planning 1
A Semantic Loss Function for Deep Learning with Symbolic Knowledge 4
A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates 3
A Spectral Approach to Gradient Estimation for Implicit Distributions 3
A Spline Theory of Deep Learning 2
A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations 3
A Two-Step Computation of the Exact GAN Wasserstein Distance 3
A Unified Framework for Structured Low-rank Matrix Learning 5
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks 3
ADMM and Accelerated ADMM as Continuous Dynamical Systems 1
Accelerated Spectral Ranking 4
Accelerating Greedy Coordinate Descent Methods 2
Accelerating Natural Gradient with Higher-Order Invariance 3
Accurate Inference for Adaptive Linear Models 3
Accurate Uncertainties for Deep Learning Using Calibrated Regression 3
Active Learning with Logged Data 4
Active Testing: An Efficient and Robust Framework for Estimating Accuracy 3
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost 6
Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits 3
Adaptive Sampled Softmax with Kernel Based Sampling 1
Adaptive Three Operator Splitting 3
Addressing Function Approximation Error in Actor-Critic Methods 4
Adversarial Attack on Graph Structured Data 3
Adversarial Distillation of Bayesian Neural Network Posteriors 5
Adversarial Learning with Local Coordinate Coding 4
Adversarial Regression with Multiple Learners 2
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks 4
Adversarial Time-to-Event Modeling 3
Adversarially Regularized Autoencoders 5
Alternating Randomized Block Coordinate Descent 2
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method 3
An Alternative View: When Does SGD Escape Local Minima? 2
An Efficient Semismooth Newton based Algorithm for Convex Clustering 4
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning 1
An Estimation and Analysis Framework for the Rasch Model 3
An Inference-Based Policy Gradient Method for Learning Options 3
An Iterative, Sketching-based Framework for Ridge Regression 3
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks 3
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model 3
Analyzing Uncertainty in Neural Machine Translation 3
Analyzing the Robustness of Nearest Neighbors to Adversarial Examples 5
Anonymous Walk Embeddings 6
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions 2
Approximate message passing for amplitude based optimization 2
Approximation Algorithms for Cascading Prediction Models 4
Approximation Guarantees for Adaptive Sampling 3
Asynchronous Byzantine Machine Learning (the case of SGD) 3
Asynchronous Decentralized Parallel Stochastic Gradient Descent 4
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization 3
Attention-based Deep Multiple Instance Learning 3
Augment and Reduce: Stochastic Inference for Large Categorical Distributions 4
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data 2
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning 3
Automatic Goal Generation for Reinforcement Learning Agents 3
Autoregressive Convolutional Neural Networks for Asynchronous Time Series 5
Autoregressive Quantile Networks for Generative Modeling 2
BOCK : Bayesian Optimization with Cylindrical Kernels 5
BOHB: Robust and Efficient Hyperparameter Optimization at Scale 6
Bandits with Delayed, Aggregated Anonymous Feedback 2
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design 4
Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent 3
Bayesian Model Selection for Change Point Detection and Clustering 1
Bayesian Optimization of Combinatorial Structures 4
Bayesian Quadrature for Multiple Related Integrals 1
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks 5
Been There, Done That: Meta-Learning with Episodic Recall 1
Best Arm Identification in Linear Bandits with Linear Dimension Dependency 3
Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams 3
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations 3
Beyond the One-Step Greedy Approach in Reinforcement Learning 2
Bilevel Programming for Hyperparameter Optimization and Meta-Learning 6
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics 1
Binary Partitions with Approximate Minimum Impurity 6
Black Box FDR 2
Black-Box Variational Inference for Stochastic Differential Equations 5
Black-box Adversarial Attacks with Limited Queries and Information 4
Blind Justice: Fairness with Encrypted Sensitive Attributes 4
Born Again Neural Networks 3
Bounding and Counting Linear Regions of Deep Neural Networks 4
Bounds on the Approximation Power of Feedforward Neural Networks 0
Bucket Renormalization for Approximate Inference 3
Budgeted Experiment Design for Causal Structure Learning 4
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates 3
CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning 4
CRVI: Convex Relaxation for Variational Inference 2
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? 3
Candidates vs. Noises Estimation for Large Multi-Class Classification Problem 5
Canonical Tensor Decomposition for Knowledge Base Completion 5
Causal Bandits with Propagating Inference 2
Celer: a Fast Solver for the Lasso with Dual Extrapolation 4
Characterizing Implicit Bias in Terms of Optimization Geometry 1
Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions 3
Chi-square Generative Adversarial Network 4
Classification from Pairwise Similarity and Unlabeled Data 5
Clipped Action Policy Gradient 3
Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization 3
Clustering Semi-Random Mixtures of Gaussians 1
CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions 2
Coded Sparse Matrix Multiplication 3
Communication-Computation Efficient Gradient Coding 3
Comparing Dynamics: Deep Neural Networks versus Glassy Systems 3
Comparison-Based Random Forests 4
Competitive Caching with Machine Learned Advice 2
Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations 2
Compiling Combinatorial Prediction Games 5
Composable Planning with Attributes 2
Composite Functional Gradient Learning of Generative Adversarial Models 5
Composite Marginal Likelihood Methods for Random Utility Models 2
Compressing Neural Networks using the Variational Information Bottleneck 3
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn’s Algorithm 4
Conditional Neural Processes 2
Conditional Noise-Contrastive Estimation of Unnormalised Models 2
Configurable Markov Decision Processes 1
Constant-Time Predictive Distributions for Gaussian Processes 6
Constrained Interacting Submodular Groupings 4
Constraining the Dynamics of Deep Probabilistic Models 2
ContextNet: Deep learning for Star Galaxy Classification 2
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing 4
Continual Reinforcement Learning with Complex Synapses 2
Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions 3
Continuous-Time Flows for Efficient Inference and Density Estimation 3
Convergence guarantees for a class of non-convex and non-smooth optimization problems 2
Convergent Tree Backup and Retrace with Function Approximation 3
Convolutional Imputation of Matrix Networks 3
Coordinated Exploration in Concurrent Reinforcement Learning 1
Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization 4
Crowdsourcing with Arbitrary Adversaries 3
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks 1
Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation 4
CyCADA: Cycle-Consistent Adversarial Domain Adaptation 2
DCFNet: Deep Neural Network with Decomposed Convolutional Filters 3
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding 5
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients 5
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations 3
Data Summarization at Scale: A Two-Stage Submodular Approach 5
Data-Dependent Stability of Stochastic Gradient Descent 1
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings 2
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning 0
Decoupled Parallel Backpropagation with Convergence Guarantee 4
Decoupling Gradient-Like Learning Rules from Representations 1
Deep Asymmetric Multi-task Feature Learning 3
Deep Bayesian Nonparametric Tracking 3
Deep Density Destructors 5
Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global 0
Deep Models of Interactions Across Sets 3
Deep One-Class Classification 3
Deep Predictive Coding Network for Object Recognition 4
Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling 4
Deep Variational Reinforcement Learning for POMDPs 3
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions 3
Delayed Impact of Fair Machine Learning 2
Dependent Relational Gamma Process Models for Longitudinal Networks 3
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches 3
Detecting and Correcting for Label Shift with Black Box Predictors 4
Detecting non-causal artifacts in multivariate linear regression models 3
DiCE: The Infinitely Differentiable Monte Carlo Estimator 3
Differentiable Abstract Interpretation for Provably Robust Neural Networks 4
Differentiable Compositional Kernel Learning for Gaussian Processes 4
Differentiable Dynamic Programming for Structured Prediction and Attention 5
Differentiable plasticity: training plastic neural networks with backpropagation 3
Differentially Private Database Release via Kernel Mean Embeddings 3
Differentially Private Identity and Equivalence Testing of Discrete Distributions 3
Differentially Private Matrix Completion Revisited 3
Dimensionality-Driven Learning with Noisy Labels 4
Discovering Interpretable Representations for Both Deep Generative and Discriminative Models 2
Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning 2
Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms 1
Disentangled Sequential Autoencoder 3
Disentangling by Factorising 2
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients 4
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs 0
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? 3
Distributed Clustering via LSH Based Data Partitioning 3
Distributed Nonparametric Regression under Communication Constraints 1
Do Outliers Ruin Collaboration? 1
Does Distributionally Robust Supervised Learning Give Robust Classifiers? 3
Dropout Training, Data-dependent Regularization, and Generalization Bounds 2
Dynamic Evaluation of Neural Sequence Models 3
Dynamic Regret of Strongly Adaptive Methods 1
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks 4
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks 3
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning 3
Efficient First-Order Algorithms for Adaptive Signal Denoising 3
Efficient Gradient-Free Variational Inference using Policy Search 3
Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation 4
Efficient Neural Architecture Search via Parameters Sharing 4
Efficient Neural Audio Synthesis 3
Efficient and Consistent Adversarial Bipartite Matching 3
Efficient end-to-end learning for quantizable representations 6
End-to-End Learning for the Deep Multivariate Probit Model 5
End-to-end Active Object Tracking via Reinforcement Learning 2
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors 3
Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory 3
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization 5
Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap 3
Escaping Saddles with Stochastic Gradients 3
Essentially No Barriers in Neural Network Energy Landscape 4
Estimation of Markov Chain via Rank-Constrained Likelihood 2
Explicit Inductive Bias for Transfer Learning with Convolutional Networks 3
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search 5
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks 5
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples 4
Extreme Learning to Rank via Low Rank Assumption 5
Fair and Diverse DPP-Based Data Summarization 3
Fairness Without Demographics in Repeated Loss Minimization 2
Fast Approximate Spectral Clustering for Dynamic Networks 2
Fast Bellman Updates for Robust MDPs 5
Fast Decoding in Sequence Models Using Discrete Latent Variables 5
Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework 2
Fast Information-theoretic Bayesian Optimisation 6
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice 4
Fast Parametric Learning with Activation Memorization 5
Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate 4
Fast Variance Reduction Method with Stochastic Batch Size 3
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow 5
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam 4
Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines 3
Feasible Arm Identification 3
Feedback-Based Tree Search for Reinforcement Learning 2
Finding Influential Training Samples for Gradient Boosted Decision Trees 3
Firing Bandits: Optimizing Crowdfunding 2
First Order Generative Adversarial Networks 3
Fitting New Speakers Based on a Short Untranscribed Sample 3
Fixing a Broken ELBO 2
Focused Hierarchical RNNs for Conditional Sequence Processing 3
Fourier Policy Gradients 1
Frank-Wolfe with Subsampling Oracle 3
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents 2
Functional Gradient Boosting based on Residual Network Perception 4
GAIN: Missing Data Imputation using Generative Adversarial Nets 4
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms 3
Gated Path Planning Networks 2
Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks 3
Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction 3
Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression 4
Generative Temporal Models with Spatial Memory for Partially Observed Environments 2
Geodesic Convolutional Shape Optimization 3
Geometry Score: A Method For Comparing Generative Adversarial Networks 5
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator 1
Goodness-of-Fit Testing for Discrete Distributions via Stein Discrepancy 3
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks 6
Gradient Coding from Cyclic MDS Codes and Expander Graphs 4
Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima 1
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers 2
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks 1
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks 1
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace 3
Gradually Updated Neural Networks for Large-Scale Image Recognition 5
Graph Networks as Learnable Physics Engines for Inference and Control 3
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models 3
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation 2
Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions 2
Hierarchical Clustering with Structural Constraints 2
Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series 4
Hierarchical Imitation and Reinforcement Learning 3
Hierarchical Long-term Video Prediction without Supervision 4
Hierarchical Multi-Label Classification Networks 3
Hierarchical Text Generation and Planning for Strategic Dialogue 2
High Performance Zero-Memory Overhead Direct Convolutions 3
High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach 4
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings 4
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures 3
INSPECTRE: Privately Estimating the Unseen 3
Image Transformer 5
Implicit Quantile Networks for Distributional Reinforcement Learning 2
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion 2
Importance Weighted Transfer of Samples in Reinforcement Learning 3
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems 2
Improved Training of Generative Adversarial Networks Using Representative Features 2
Improved large-scale graph learning through ridge spectral sparsification 3
Improved nearest neighbor search using auxiliary information and priority functions 3
Improving Optimization for Models With Continuous Symmetry Breaking 4
Improving Regression Performance with Distributional Losses 2
Improving Sign Random Projections With Additional Information 3
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising 4
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms 3
Inductive Two-Layer Modeling with Parametric Bregman Transfer 2
Inference Suboptimality in Variational Autoencoders 2
Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization 3
Inter and Intra Topic Structure Learning with Word Embeddings 4
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) 1
Invariance of Weight Distributions in Rectified MLPs 2
Investigating Human Priors for Playing Video Games 2
Is Generator Conditioning Causally Related to GAN Performance? 3
Iterative Amortized Inference 5
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets 3
Junction Tree Variational Autoencoder for Molecular Graph Generation 3
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning 5
K-means clustering using random matrix sparsification 3
Katyusha X: Simple Momentum Method for Stochastic Sum-of-Nonconvex Optimization 1
Kernel Recursive ABC: Point Estimation with Intractable Likelihood 4
Kernelized Synaptic Weight Matrices 4
Knowledge Transfer with Jacobian Matching 1
Kronecker Recurrent Units 3
LaVAN: Localized and Visible Adversarial Noise 3
Large-Scale Cox Process Inference using Variational Fourier Features 3
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion 6
Latent Space Policies for Hierarchical Reinforcement Learning 3
LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration 5
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations 3
Learning Adversarially Fair and Transferable Representations 4
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach 3
Learning Compact Neural Networks with Regularization 1
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry 3
Learning Deep ResNet Blocks Sequentially using Boosting Theory 5
Learning Diffusion using Hyperparameters 2
Learning Dynamics of Linear Denoising Autoencoders 3
Learning Equations for Extrapolation and Control 3
Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling 3
Learning Implicit Generative Models with the Method of Learned Moments 3
Learning Independent Causal Mechanisms 3
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations 4
Learning Localized Spatio-Temporal Models From Streaming Data 4
Learning Long Term Dependencies via Fourier Recurrent Units 3
Learning Longer-term Dependencies in RNNs with Auxiliary Losses 3
Learning Low-Dimensional Temporal Representations 4
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time 2
Learning Memory Access Patterns 2
Learning One Convolutional Layer with Overlapping Patches 2
Learning Policy Representations in Multiagent Systems 3
Learning Registered Point Processes from Idiosyncratic Observations 2
Learning Representations and Generative Models for 3D Point Clouds 4
Learning Semantic Representations for Unsupervised Domain Adaptation 4
Learning Steady-States of Iterative Algorithms over Graphs 5
Learning a Mixture of Two Multinomial Logits 0
Learning and Memorization 2
Learning by Playing Solving Sparse Reward Tasks from Scratch 1
Learning in Integer Latent Variable Models with Nested Automatic Differentiation 3
Learning in Reproducing Kernel Kreı̆n Spaces 3
Learning the Reward Function for a Misspecified Model 2
Learning to Act in Decentralized Partially Observable MDPs 4
Learning to Branch 5
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems 3
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation 4
Learning to Explore via Meta-Policy Gradient 4
Learning to Optimize Combinatorial Functions 2
Learning to Reweight Examples for Robust Deep Learning 4
Learning to Speed Up Structured Output Prediction 4
Learning to search with MCTSnets 1
Learning unknown ODE models with Gaussian processes 4
Learning with Abandonment 2
Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator 2
Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games 1
Level-Set Methods for Finite-Sum Constrained Convex Optimization 3
Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms 4
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data 3
Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design 3
Linear Spectral Estimators and an Application to Phase Retrieval 2
Lipschitz Continuity in Model-based Reinforcement Learning 3
Local Convergence Properties of SAGA/Prox-SVRG and Acceleration 3
Local Density Estimation in High Dimensions 3
Local Private Hypothesis Testing: Chi-Square Tests 2
Locally Private Hypothesis Testing 1
Loss Decomposition for Fast Learning in Large Output Spaces 3
Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering 3
Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees 2
MAGAN: Aligning Biological Manifolds 2
MISSION: Ultra Large-Scale Feature Selection using Count-Sketches 5
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning 3
Machine Theory of Mind 0
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits 1
Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data 3
Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances 4
Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order 0
Max-Mahalanobis Linear Discriminant Analysis Networks 4
Mean Field Multi-Agent Reinforcement Learning 3
Measuring abstract reasoning in neural networks 4
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels 4
Message Passing Stein Variational Gradient Descent 3
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory 4
Minibatch Gibbs Sampling on Large Graphical Models 2
Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models 3
Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates 3
Mitigating Bias in Adaptive Data Gathering via Differential Privacy 1
Mix & Match Agent Curricula for Reinforcement Learning 1
Mixed batches and symmetric discriminators for GAN training 2
Model-Level Dual Learning 4
Modeling Others using Oneself in Multi-Agent Reinforcement Learning 3
Modeling Sparse Deviations for Compressed Sensing using Generative Models 3
More Robust Doubly Robust Off-policy Evaluation 2
Multi-Fidelity Black-Box Optimization with Hierarchical Partitions 5
Multicalibration: Calibration for the (Computationally-Identifiable) Masses 1
Mutual Information Neural Estimation 3
Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices 1
Nearly Optimal Robust Subspace Tracking 3
NetGAN: Generating Graphs via Random Walks 5
Network Global Testing by Counting Graphlets 2
Neural Autoregressive Flows 3
Neural Dynamic Programming for Musical Self Similarity 4
Neural Inverse Rendering for General Reflectance Photometric Stereo 3
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions 2
Neural Program Synthesis from Diverse Demonstration Videos 2
Neural Relational Inference for Interacting Systems 4
Noise2Noise: Learning Image Restoration without Clean Data 4
Noisin: Unbiased Regularization for Recurrent Neural Networks 4
Noisy Natural Gradient as Variational Inference 3
Non-convex Conditional Gradient Sliding 3
Non-linear motor control by local learning in spiking neural networks 2
Nonconvex Optimization for Regression with Fairness Constraints 4
Nonoverlap-Promoting Variable Selection 4
Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information 4
Nonparametric variable importance using an augmented neural network with multi-task learning 3
Not All Samples Are Created Equal: Deep Learning with Importance Sampling 5
Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care 2
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples 3
On Acceleration with Noise-Corrupted Gradients 2
On Learning Sparsely Used Dictionaries from Incomplete Samples 3
On Matching Pursuit and Coordinate Descent 3
On Nesting Monte Carlo Estimators 0
On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups 0
On the Implicit Bias of Dropout 2
On the Limitations of First-Order Approximation in GAN Dynamics 1
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization 2
On the Power of Over-parametrization in Neural Networks with Quadratic Activation 0
On the Relationship between Data Efficiency and Error for Uncertainty Sampling 4
On the Spectrum of Random Features Maps of High Dimensional Data 2
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo 3
One-Shot Segmentation in Clutter 4
Online Convolutional Sparse Coding with Sample-Dependent Dictionary 5
Online Learning with Abstention 3
Online Linear Quadratic Control 2
Open Category Detection with PAC Guarantees 5
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods 2
Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces 1
Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data 3
Optimization Landscape and Expressivity of Deep CNNs 2
Optimization, fast and slow: optimally switching between local and Bayesian optimization 3
Optimizing the Latent Space of Generative Networks 2
Orthogonal Machine Learning: Power and Limitations 3
Orthogonal Recurrent Neural Networks with Scaled Cayley Transform 4
Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis 3
Out-of-sample extension of graph adjacency spectral embedding 1
Overcoming Catastrophic Forgetting with Hard Attention to the Task 5
PDE-Net: Learning PDEs from Data 2
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos 3
Parallel Bayesian Network Structure Learning 3
Parallel WaveNet: Fast High-Fidelity Speech Synthesis 3
Parallel and Streaming Algorithms for K-Core Decomposition 3
Parameterized Algorithms for the Matrix Completion Problem 0
Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering 4
Path Consistency Learning in Tsallis Entropy Regularized MDPs 3
Path-Level Network Transformation for Efficient Architecture Search 4
Pathwise Derivatives Beyond the Reparameterization Trick 3
PixelSNAIL: An Improved Autoregressive Generative Model 3
Policy Optimization as Wasserstein Gradient Flows 4
Policy Optimization with Demonstrations 2
Policy and Value Transfer in Lifelong Reinforcement Learning 3
Practical Contextual Bandits with Regression Oracles 4
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning 4
Predict and Constrain: Modeling Cardinality in Deep Structured Prediction 3
Prediction Rule Reshaping 5
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness 2
Probabilistic Boolean Tensor Decomposition 5
Probabilistic Recurrent State-Space Models 3
Probably Approximately Metric-Fair Learning 0
Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs 1
Programmatically Interpretable Reinforcement Learning 3
Progress & Compress: A scalable framework for continual learning 1
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity 4
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy 1
Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope 5
Provable Variable Selection for Streaming Features 2
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back 4
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning 1
QuantTree: Histograms for Change Detection in Multivariate Data Streams 4
Quasi-Monte Carlo Variational Inference 3
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift 4
RLlib: Abstractions for Distributed Reinforcement Learning 5
Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors 2
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks 3
Randomized Block Cubic Newton Method 2
Ranking Distributions based on Noisy Sorting 3
Rapid Adaptation with Conditionally Shifted Neurons 2
Rates of Convergence of Spectral Methods for Graphon Estimation 2
Rectify Heterogeneous Models with Semantic Mapping 1
Recurrent Predictive State Policy Networks 4
Regret Minimization for Partially Observable Deep Reinforcement Learning 3
Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control 1
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training 3
Representation Learning on Graphs with Jumping Knowledge Networks 3
Representation Tradeoffs for Hyperbolic Embeddings 3
Residual Unfairness in Fair Machine Learning from Prejudiced Data 1
Revealing Common Statistical Behaviors in Heterogeneous Populations 4
Reviving and Improving Recurrent Back-Propagation 5
Riemannian Stochastic Recursive Gradient Algorithm 6
Robust and Scalable Models of Microbiome Dynamics 2
SADAGRAD: Strongly Adaptive Stochastic Gradient Methods 3
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate 2
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation 3
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption 3
SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions 2
SQL-Rank: A Listwise Approach to Collaborative Ranking 6
Safe Element Screening for Submodular Function Minimization 4
Scalable Bilinear Pi Learning Using State and Action Features 1
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints 2
Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF) 6
Scalable approximate Bayesian inference for particle tracking data 4
Selecting Representative Examples for Program Synthesis 2
Self-Bounded Prediction Suffix Tree via Approximate String Matching 4
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings 2
Self-Imitation Learning 4
Semi-Amortized Variational Autoencoders 4
Semi-Implicit Variational Inference 5
Semi-Supervised Learning on Data Streams via Temporal Label Propagation 4
Semi-Supervised Learning via Compact Latent Space Clustering 4
Semiparametric Contextual Bandits 3
Shampoo: Preconditioned Stochastic Tensor Optimization 4
Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit 3
Smoothed Action Value Functions for Learning Gaussian Policies 3
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor 4
Solving Partial Assignment Problems using Random Clique Complexes 4
Sound Abstraction and Decomposition of Probabilistic Programs 2
SparseMAP: Differentiable Sparse Structured Inference 5
Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection 4
Spectrally Approximating Large Graphs with Smaller Graphs 3
Spline Filters For End-to-End Deep Learning 3
Spotlight: Optimizing Device Placement for Training Deep Neural Networks 4
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks 4
Stability and Generalization of Learning Algorithms that Converge to Global Optima 0
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization 5
Stagewise Safe Bayesian Optimization with Gaussian Processes 2
State Abstractions for Lifelong Reinforcement Learning 2
State Space Gaussian Processes with Non-Gaussian Likelihood 7
Stein Points 1
Stein Variational Gradient Descent Without Gradient 3
Stein Variational Message Passing for Continuous Graphical Models 3
Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization 4
Stochastic Proximal Algorithms for AUC Maximization 4
Stochastic Training of Graph Convolutional Networks with Variance Reduction 6
Stochastic Variance-Reduced Cubic Regularized Newton Methods 3
Stochastic Variance-Reduced Hamilton Monte Carlo Methods 3
Stochastic Variance-Reduced Policy Gradient 4
Stochastic Video Generation with a Learned Prior 4
Stochastic Wasserstein Barycenters 2
StrassenNets: Deep Learning with a Multiplication Budget 5
Streaming Principal Component Analysis in Noisy Setting 3
Stronger Generalization Bounds for Deep Nets via a Compression Approach 3
Structured Control Nets for Deep Reinforcement Learning 3
Structured Evolution with Compact Architectures for Scalable Policy Optimization 2
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction 2
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors 2
Structured Variationally Auto-encoded Optimization 5
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis 2
Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering 3
Subspace Embedding and Linear Regression with Orlicz Norm 3
Synthesizing Programs for Images using Reinforced Adversarial Learning 1
Synthesizing Robust Adversarial Examples 3
TACO: Learning Task Decomposition via Temporal Alignment for Control 0
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service 5
Tempered Adversarial Networks 2
Temporal Poisson Square Root Graphical Models 1
Testing Sparsity over Known and Unknown Bases 3
The Dynamics of Learning: A Random Matrix Approach 2
The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference 0
The Generalization Error of Dictionary Learning with Moreau Envelopes 0
The Hidden Vulnerability of Distributed Learning in Byzantium 3
The Hierarchical Adaptive Forgetting Variational Filter 2
The Limits of Maxing, Ranking, and Preference Learning 2
The Mechanics of n-Player Differentiable Games 3
The Mirage of Action-Dependent Baselines in Reinforcement Learning 3
The Multilinear Structure of ReLU Networks 0
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning 3
The Uncertainty Bellman Equation and Exploration 4
The Weighted Kendall and High-order Kernels for Permutations 3
The Well-Tempered Lasso 2
Theoretical Analysis of Image-to-Image Translation with Adversarial Learning 0
Theoretical Analysis of Sparse Subspace Clustering with Missing Entries 1
Thompson Sampling for Combinatorial Semi-Bandits 2
Tight Regret Bounds for Bayesian Optimization in One Dimension 1
Tighter Variational Bounds are Not Necessarily Better 2
Time Limits in Reinforcement Learning 3
To Understand Deep Learning We Need to Understand Kernel Learning 2
Topological mixture estimation 3
Towards Binary-Valued Gates for Robust LSTM Training 5
Towards Black-box Iterative Machine Teaching 2
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron 2
Towards Fast Computation of Certified Robustness for ReLU Networks 4
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication 3
Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings 5
Training Neural Machines with Trace-Based Supervision 2
Transfer Learning via Learning to Transfer 3
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement 2
Transformation Autoregressive Networks 4
Tree Edit Distance Learning via Adaptive Symbol Embeddings 5
Tropical Geometry of Deep Neural Networks 0
Unbiased Objective Estimation in Predictive Optimization 5
Understanding Generalization and Optimization Performance of Deep CNNs 0
Understanding and Simplifying One-Shot Architecture Search 4
Understanding the Loss Surface of Neural Networks for Binary Classification 0
Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control 1
Using Inherent Structures to design Lean 2-layer RBMs 4
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning 4
Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach 4
Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization 6
Variational Bayesian dropout: pitfalls and fixes 0
Variational Inference and Model Selection with Generalized Evidence Bounds 2
Variational Network Inference: Strong and Stable with Concrete Support 2
Video Prediction with Appearance and Motion Conditions 5
Visualizing and Understanding Atari Agents 3
WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models 4
WSNet: Compact and Efficient Networks Through Weight Sampling 4
Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer 1
Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy? 3
Weightless: Lossy weight encoding for deep neural network compression 4
Which Training Methods for GANs do actually Converge? 1
Yes, but Did It Work?: Evaluating Variational Inference 3
oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis 3
prDeep: Robust Phase Retrieval with a Flexible Deep Network 5
signSGD: Compressed Optimisation for Non-Convex Problems 5