ICML 2019

Session:

Event type:

Hide breaks and receptions:

Day:

Show All »

June 9, 2019 Expo schedule » LatinX, Queer in AI and WiML Events »

Indicates the beginning of a session

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

Thu Jun 13, 2019