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

Thu Jun 13, 2019