ICML 2019

Search Schedule »

Search:

Session:

Event type:

Hide breaks and receptions:

Day:

Show All »

June 9, 2019 Expo schedule » New in ML »

Timezone: America/Los_Angeles »

Indicates the beginning of a session

Time	Hall B	Room 104	Hall A	Grand Ballroom	Room 101	Room 201	Room 102	Seaside Ballroom	Room 103	Pacific Ballroom
Thu Jun 13, 2019
09:00 AM (Orals)	Reinforcement Learning Batch Policy Learning under Constraints	Non-convex Optimization Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning	Deep Generative Models State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations	Interpretability Neural Network Attributions: A Causal Perspective	Monte Carlo Methods Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions	Applications Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random	Online Learning Matrix-Free Preconditioning in Online Learning	Privacy and Fairness On Sparse Linear Regression in the Local Differential Privacy Model	Supervised and Transfer Learning Geometric Losses for Distributional Learning
09:20 AM (Orals)	Quantifying Generalization in Reinforcement Learning	Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization	Variational Laplace Autoencoders	Towards a Deep and Unified Understanding of Deep Neural Models in NLP	Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization	Linear-Complexity Data-Parallel Earth Mover's Distance Approximations	Online Convex Optimization in Adversarial Markov Decision Processes	Differentially Private Empirical Risk Minimization with Non-convex Loss Functions	Classification from Positive, Unlabeled and Biased Negative Data
09:25 AM (Orals)	Learning Latent Dynamics for Planning from Pixels	Neuron birth-death dynamics accelerates gradient descent and converges asymptotically	Latent Normalizing Flows for Discrete Sequences	Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation	Unifying Orthogonal Monte Carlo Methods	Model Comparison for Semantic Grouping	Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games	Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy	Complementary-Label Learning for Arbitrary Losses and Models
09:30 AM (Orals)	Projections for Approximate Policy Iteration Algorithms	Width Provably Matters in Optimization for Deep Linear Neural Networks	Multi-objective training of Generative Adversarial Networks with multiple discriminators	Functional Transparency for Structured Data: a Game-Theoretic Approach	Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits	RaFM: Rank-Aware Factorization Machines	Online Learning with Sleeping Experts and Feedback Graphs	Differentially Private Learning of Geometric Concepts	Learning to Infer Program Sketches
09:35 AM (Orals)	Learning Structured Decision Problems with Unawareness	Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?	Learning Discrete and Continuous Factors of Data via Alternating Disentanglement	Exploring interpretable LSTM neural networks over multi-variable data	Metropolis-Hastings Generative Adversarial Networks	CAB: Continuous Adaptive Blending for Policy Evaluation and Learning	Incremental Randomized Sketching for Online Kernel Learning	Toward Controlling Discrimination in Online Ad Auctions	Hierarchically Structured Meta-learning
09:40 AM (Orals)	Calibrated Model-Based Deep Reinforcement Learning	Power k-Means Clustering	Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables	TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing	Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets	MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement	Adaptive Scale-Invariant Online Algorithms for Learning Linear Models	Learning Optimal Fair Policies	Bridging Theory and Algorithm for Domain Adaptation
10:00 AM (Orals)	Reinforcement Learning in Configurable Continuous Environments	Distributed Learning over Unreliable Networks	Graphite: Iterative Generative Modeling of Graphs	Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute	Replica Conditional Sequential Monte Carlo	Neural Separation of Observed and Unobserved Distributions	Online Control with Adversarial Disturbances	Fairness-Aware Learning for Continuous Attributes and Treatments	Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
10:05 AM (Orals)	Target-Based Temporal-Difference Learning	Escaping Saddle Points with Adaptive Gradient Methods	Hybrid Models with Deep and Invertible Features	State-Regularized Recurrent Neural Networks	A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes	Almost Unsupervised Text to Speech and Automatic Speech Recognition	Adversarial Online Learning with noise	Fairness risk measures	Learning What and Where to Transfer
10:10 AM (Orals)	Iterative Linearized Control: Stable Algorithms and Complexity Guarantees	$\texttt{DoubleSqueeze}$: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression	MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets	Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation	Adaptive Antithetic Sampling for Variance Reduction	AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss	Online Variance Reduction with Mixtures
10:15 AM (Orals)	Finding Options that Minimize Planning Time	Model Function Based Conditional Gradient Method with Armijo-like Line Search	On Scalable and Efficient Computation of Large Scale Optimal Transport	On the Connection Between Adversarial Robustness and Saliency Map Interpretability	Accelerated Flow for Probability Distributions	A fully differentiable beam search decoder	Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
11:00 AM (Orals)	Deep Sequence Models Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement	Applications: Natural Language Processing Analogies Explained: Towards Understanding Word Embeddings	Deep Learning Understanding and correcting pathologies in the training of learned optimizers	Deep Learning Theory Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem	Optimization and Graphical Models Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering	Ranking and Preference Learning Scaling Up Ordinal Embedding: A Landmark Approach	Online Learning Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret	Fairness Proportionally Fair Clustering	Unsupervised Learning DBSCAN++: Towards fast and scalable density clustering
11:20 AM (Orals)	Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs	Parameter-Efficient Transfer Learning for NLP	Demystifying Dropout	On the Spectral Bias of Neural Networks	Dimensionality Reduction for Tukey Regression	Learning to select for a predefined ranking	Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems	Stable and Fair Classification	Concrete Autoencoders: Differentiable Feature Selection and Reconstruction
11:25 AM (Orals)	Meta-Learning Neural Bloom Filters	Efficient On-Device Models using Neural Projections	Ladder Capsule Network	Recursive Sketches for Modular Deep Learning	Efficient Full-Matrix Adaptive Regularization	Mallows ranking models: maximum likelihood estimate and regeneration	Adaptive Regret of Convex and Smooth Functions	Flexibly Fair Representation Learning by Disentanglement	Gromov-Wasserstein Learning for Graph Matching and Node Embedding
11:30 AM (Orals)	CoT: Cooperative Training for Generative Modeling of Discrete Data	Deep Residual Output Layers for Neural Language Generation	Unreproducible Research is Reproducible	Zero-Shot Knowledge Distillation in Deep Networks	Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms	Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models	Online Adaptive Principal Component Analysis and Its extensions	Fair Regression: Quantitative Definitions and Reduction-Based Algorithms	Spectral Clustering of Signed Graphs via Matrix Power Means
11:35 AM (Orals)	Non-Monotonic Sequential Text Generation	Improving Neural Language Modeling via Adversarial Training	Geometric Scattering for Graph Data Analysis	A Convergence Theory for Deep Learning via Over-Parameterization	Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations	Fast Algorithm for Generalized Multinomial Models with Ranking Data	POLITEX: Regret Bounds for Policy Iteration using Expert Prediction	Fairness without Harm: Decoupled Classifiers with Preference Guarantees	Coresets for Ordered Weighted Clustering
11:40 AM (Orals)	Insertion Transformer: Flexible Sequence Generation via Insertion Operations	Mixture Models for Diverse Machine Translation: Tricks of the Trade	Robust Inference via Generative Classifiers for Handling Noisy Labels	A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks	Robust Estimation of Tree Structured Gaussian Graphical Models	Graph Resistance and Learning from Pairwise Comparisons	Anytime Online-to-Batch, Optimism and Acceleration	Differentially Private Fair Learning	Fair k-Center Clustering for Data Summarization
12:00 PM (Orals)	Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models	MASS: Masked Sequence to Sequence Pre-training for Language Generation	LIT: Learned Intermediate Representation Training for Model Compression	Approximation and non-parametric estimation of ResNet-type convolutional neural networks	Spectral Approximate Inference	Learning Context-dependent Label Permutations for Multi-label Classification	Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints	Obtaining Fairness using Optimal Transport Theory	A Better k-means++ Algorithm via Local Search
12:05 PM (Orals)	Trainable Decoding of Sets of Sequences for Neural Sequence Models	Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops	Analyzing and Improving Representations with the Soft Nearest Neighbor Loss	Global Convergence of Block Coordinate Descent in Deep Learning	Partially Linear Additive Gaussian Graphical Models	Discovering Context Effects from Raw Choice Data	Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning	Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions	Kernel Normalized Cut: a Theoretical Revisit
12:10 PM (Orals)	Learning to Generalize from Sparse and Underspecified Rewards	MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization	What is the Effect of Importance Weighting in Deep Learning?	Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians	DAG-GNN: DAG Structure Learning with Graph Neural Networks	On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference	Adaptive Sensor Placement for Continuous Spaces	On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning	Guarantees for Spectral Clustering with Fairness Constraints
12:15 PM (Orals)	Efficient Training of BERT by Progressively Stacking	CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network	Similarity of Neural Network Representations Revisited	On the Limitations of Representing Functions on Sets	Random Walks on Hypergraphs with Edge-Dependent Vertex Weights	Learning Distance for Sequences by Learning a Ground Metric	Scale-free adaptive planning for deterministic dynamics & discounted rewards	Making Decisions that Reduce Discriminatory Impacts	Supervised Hierarchical Clustering with Exponential Linkage
02:00 PM (Invited Talks)			What 4 year olds can do and AI can’t (yet)
03:00 PM (Invited Talks, Orals)			Best Paper Rates of Convergence for Sparse Variational Gaussian Process Regression
04:00 PM (Orals)	Bandits and Multiagent Learning Decentralized Exploration in Multi-Armed Bandits	Unsupervised Learning COMIC: Multi-view Clustering Without Parameter Selection	Representation Learning Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations	Bayesian Deep Learning Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering			Learning Theory Communication-Constrained Inference and the Role of Shared Randomness	Optimization Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications
04:20 PM (Orals)	Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback	The Wasserstein Transform	Distributed, Egocentric Representations of Graphs for Detecting Critical Structures	Nonparametric Bayesian Deep Networks with Local Competition			Learning and Data Selection in Big Datasets	Online Algorithms for Rent-Or-Buy with Expert Advice
04:25 PM (Orals)	Exploiting structure of uncertainty for efficient matroid semi-bandits	Sequential Facility Location: Approximate Submodularity and Greedy Algorithm	Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities	Good Initializations of Variational Bayes for Deep Models			Sublinear quantum algorithms for training linear and kernel-based classifiers	Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity
04:30 PM (Orals)	PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits	Neural Collaborative Subspace Clustering	Multi-Object Representation Learning with Iterative Variational Inference	Dropout as a Structured Shrinkage Prior			Agnostic Federated Learning	Categorical Feature Compression via Submodular Optimization
04:35 PM (Orals)	Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model	Unsupervised Deep Learning by Neighbourhood Discovery	Cross-Domain 3D Equivariant Image Embeddings	ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables			Discovering Conditionally Salient Features with Statistical Guarantees	Multi-Frequency Phase Synchronization
04:40 PM (Orals)	Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning	Autoregressive Energy Machines	Loss Landscapes of Regularized Linear Autoencoders	On Variational Bounds of Mutual Information			A Theoretical Analysis of Contrastive Unsupervised Representation Learning	Faster Algorithms for Binary Matrix Factorization
05:00 PM (Orals)	TarMAC: Targeted Multi-Agent Communication	Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization	Hyperbolic Disk Embeddings for Directed Acyclic Graphs	Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation			The information-theoretic value of unlabeled data in semi-supervised learning
05:05 PM (Orals)	QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning	Noise2Self: Blind Denoising by Self-Supervision	LatentGNN: Learning Efficient Non-local Relations for Visual Recognition	Hierarchical Importance Weighted Autoencoders			Unsupervised Label Noise Modeling and Loss Correction	Guided evolutionary strategies: augmenting random search with surrogate gradients
05:10 PM (Orals)	Actor-Attention-Critic for Multi-Agent Reinforcement Learning	Learning Dependency Structures for Weak Supervision Models	Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness	Faster Attend-Infer-Repeat with Tractable Probabilistic Models			Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment	Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces
05:15 PM (Orals)	Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning	Geometry and Symmetry in Short-and-Sparse Deconvolution	Lorentzian Distance Learning for Hyperbolic Representations	Understanding Priors in Bayesian Neural Networks at the Unit Level			Pareto Optimal Streaming Unsupervised Classification	Semi-Cyclic Stochastic Gradient Descent
06:30 PM (Posters)										Posters Thu

Thu Jun 13, 2019