Toggle Poster Visibility
Oral
Tue Jun 11 10:00 AM -- 10:20 AM (PDT) @ Hall A
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Room 103
Refined Complexity of PCA with Outliers
[
Video]
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Seaside Ballroom
Data Shapley: Equitable Valuation of Data for Machine Learning
[
Video]
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Room 104
PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Room 102
Regret Circuits: Composability of Regret Minimizers
[
Slides]
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Grand Ballroom
Adversarial Attacks on Node Embeddings via Graph Poisoning
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Room 101
A Contrastive Divergence for Combining Variational Inference and MCMC
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Room 201
Validating Causal Inference Models via Influence Functions
In
Applications
[
Video]
Oral
Tue Jun 11 11:00 AM -- 11:20 AM (PDT) @ Hall A
SelectiveNet: A Deep Neural Network with an Integrated Reject Option
[
Video]
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Seaside Ballroom
Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Room 102
Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function
[
Slides]
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Room 104
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Grand Ballroom
First-Order Adversarial Vulnerability of Neural Networks and Input Dimension
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Room 101
Calibrated Approximate Bayesian Inference
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Hall A
Manifold Mixup: Better Representations by Interpolating Hidden States
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Room 103
On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms
Oral
Tue Jun 11 11:20 AM -- 11:25 AM (PDT) @ Room 201
Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks
In
Applications
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Room 201
Learning to Groove with Inverse Sequence Transformations
In
Applications
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Seaside Ballroom
Metric-Optimized Example Weights
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Room 104
Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Grand Ballroom
On Certifying Non-Uniform Bounds against Adversarial Attacks
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Room 101
Moment-Based Variational Inference for Markov Jump Processes
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Room 103
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Hall A
Processing Megapixel Images with Deep Attention-Sampling Models
Oral
Tue Jun 11 11:25 AM -- 11:30 AM (PDT) @ Room 102
Stable-Predictive Optimistic Counterfactual Regret Minimization
[
Slides]
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Room 102
When Samples Are Strategically Selected
[
Slides]
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Seaside Ballroom
Improving Model Selection by Employing the Test Data
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Grand Ballroom
Improving Adversarial Robustness via Promoting Ensemble Diversity
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Room 201
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI
In
Applications
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Room 103
Teaching a black-box learner
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Room 101
Understanding MCMC Dynamics as Flows on the Wasserstein Space
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Hall A
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
Oral
Tue Jun 11 11:30 AM -- 11:35 AM (PDT) @ Room 104
Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Room 103
PAC Learnability of Node Functions in Networked Dynamical Systems
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Room 104
Nonconvex Variance Reduced Optimization with Arbitrary Sampling
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Seaside Ballroom
Topological Data Analysis of Decision Boundaries with Application to Model Selection
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Room 201
HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving
In
Applications
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Room 102
Statistical Foundations of Virtual Democracy
[
Slides]
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Grand Ballroom
Adversarial camera stickers: A physical camera-based attack on deep learning systems
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Hall A
Online Meta-Learning
Oral
Tue Jun 11 11:35 AM -- 11:40 AM (PDT) @ Room 101
LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Room 103
Online learning with kernel losses
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Room 104
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
[
Video]
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Room 201
Molecular Hypergraph Grammar with Its Application to Molecular Optimization
In
Applications
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Room 102
Optimal Auctions through Deep Learning
[
Slides]
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Hall A
Training Neural Networks with Local Error Signals
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Grand Ballroom
Adversarial examples from computational constraints
[
Video]
Oral
Tue Jun 11 11:40 AM -- 12:00 PM (PDT) @ Room 101
Amortized Monte Carlo Integration
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Seaside Ballroom
Sparse Extreme Multi-label Learning with Oracle Property
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Room 101
Stein Point Markov Chain Monte Carlo
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Grand Ballroom
POPQORN: Quantifying Robustness of Recurrent Neural Networks
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Room 104
A Composite Randomized Incremental Gradient Method
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Room 201
Graph Neural Network for Music Score Data and Modeling Expressive Piano Performance
In
Applications
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Room 103
Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates
Oral
Tue Jun 11 12:00 PM -- 12:05 PM (PDT) @ Hall A
GMNN: Graph Markov Neural Networks
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Grand Ballroom
Using Pre-Training Can Improve Model Robustness and Uncertainty
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Room 103
Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Hall A
Self-Attention Graph Pooling
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Room 201
Learning to Prove Theorems via Interacting with Proof Assistants
In
Applications
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Room 102
Learning to bid in revenue-maximizing auctions
[
Slides]
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Room 104
Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Seaside Ballroom
Shape Constraints for Set Functions
Oral
Tue Jun 11 12:05 PM -- 12:10 PM (PDT) @ Room 101
Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Room 201
Circuit-GNN: Graph Neural Networks for Distributed Circuit Design
In
Applications
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Room 104
Multiplicative Weights Updates as a distributed constrained optimization algorithm: Convergence to second-order stationary points almost always
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Room 102
Open-ended learning in symmetric zero-sum games
[
Slides]
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Room 101
Particle Flow Bayes' Rule
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Room 103
Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Hall A
Combating Label Noise in Deep Learning using Abstention
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Grand Ballroom
Generalized No Free Lunch Theorem for Adversarial Robustness
Oral
Tue Jun 11 12:10 PM -- 12:15 PM (PDT) @ Seaside Ballroom
On The Power of Curriculum Learning in Training Deep Networks
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Room 104
Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Room 102
Deep Counterfactual Regret Minimization
[
Slides]
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Grand Ballroom
PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Hall A
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Room 101
Correlated Variational Auto-Encoders
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Room 103
Maximum Likelihood Estimation for Learning Populations of Parameters
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Room 201
Learning to Optimize Multigrid PDE Solvers
In
Applications
Oral
Tue Jun 11 12:15 PM -- 12:20 PM (PDT) @ Seaside Ballroom
Voronoi Boundary Classification: A High-Dimensional Geometric Approach via Weighted Monte Carlo Integration
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Room 102
Generalized Approximate Survey Propagation for High-Dimensional Estimation
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Seaside Ballroom
Robust Decision Trees Against Adversarial Examples
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Hall A
Self-Attention Generative Adversarial Networks
[
Video]
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Room 103
Projection onto Minkowski Sums with Application to Constrained Learning
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Room 201
A Block Coordinate Descent Proximal Method for Simultaneous Filtering and Parameter Estimation
In
Time Series
[
Video]
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Room 101
Towards a Unified Analysis of Random Fourier Features
[
Video]
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Grand Ballroom
On Learning Invariant Representations for Domain Adaptation
[
Video]
Oral
Tue Jun 11 02:00 PM -- 02:20 PM (PDT) @ Room 104
Safe Policy Improvement with Baseline Bootstrapping
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Grand Ballroom
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Room 104
Distributional Reinforcement Learning for Efficient Exploration
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Room 201
Learning Hawkes Processes Under Synchronization Noise
In
Time Series
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Room 102
Boosted Density Estimation Remastered
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Seaside Ballroom
Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Room 103
Blended Conditonal Gradients
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Hall A
Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
Oral
Tue Jun 11 02:20 PM -- 02:25 PM (PDT) @ Room 101
Learning deep kernels for exponential family densities
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Seaside Ballroom
Look Ma, No Latent Variables: Accurate Cutset Networks via Compilation
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Room 101
Bayesian Deconditional Kernel Mean Embeddings
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Room 104
Optimistic Policy Optimization via Multiple Importance Sampling
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Room 102
Inference and Sampling of $K_{33}$-free Ising Models
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Grand Ballroom
Adversarial Generation of Time-Frequency Features with application in audio synthesis
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Room 103
Acceleration of SVRG and Katyusha X by Inexact Preconditioning
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Room 201
Generative Adversarial User Model for Reinforcement Learning Based Recommendation System
In
Time Series
Oral
Tue Jun 11 02:25 PM -- 02:30 PM (PDT) @ Hall A
High-Fidelity Image Generation With Fewer Labels
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Room 103
Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Hall A
Revisiting precision recall definition for generative modeling
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Room 201
A Statistical Investigation of Long Memory in Language and Music
In
Time Series
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Room 104
Neural Logic Reinforcement Learning
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Room 102
Random Matrix Improved Covariance Estimation for a Large Class of Metrics
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Room 101
A Kernel Perspective for Regularizing Deep Neural Networks
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Grand Ballroom
On the Universality of Invariant Networks
Oral
Tue Jun 11 02:30 PM -- 02:35 PM (PDT) @ Seaside Ballroom
Optimal Transport for structured data with application on graphs
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Room 102
Dual Entangled Polynomial Code: Three-Dimensional Coding for Distributed Matrix Multiplication
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Seaside Ballroom
Learning Optimal Linear Regularizers
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Hall A
Wasserstein of Wasserstein Loss for Learning Generative Models
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Room 103
A Conditional-Gradient-Based Augmented Lagrangian Framework
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Grand Ballroom
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Room 104
Learning to Collaborate in Markov Decision Processes
Oral
Tue Jun 11 02:35 PM -- 02:40 PM (PDT) @ Room 101
A Persistent Weisfeiler--Lehman Procedure for Graph Classification
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Room 101
Rehashing Kernel Evaluation in High Dimensions
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Grand Ballroom
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
[
Video]
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Room 201
Weakly-Supervised Temporal Localization via Occurrence Count Learning
In
Time Series
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Room 102
Neural Joint Source-Channel Coding
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Hall A
Flat Metric Minimization with Applications in Generative Modeling
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Room 103
SGD: General Analysis and Improved Rates
[
Video]
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Seaside Ballroom
On Symmetric Losses for Learning from Corrupted Labels
Oral
Tue Jun 11 02:40 PM -- 03:00 PM (PDT) @ Room 104
Predictor-Corrector Policy Optimization
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Room 102
Doubly-Competitive Distribution Estimation
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Room 101
Large-Scale Sparse Kernel Canonical Correlation Analysis
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Room 104
Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Room 103
Curvature-Exploiting Acceleration of Elastic Net Computations
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Room 201
Switching Linear Dynamics for Variational Bayes Filtering
In
Time Series
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Hall A
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Seaside Ballroom
AUCµ: A Performance Metric for Multi-Class Machine Learning Models
[
Slides]
Oral
Tue Jun 11 03:00 PM -- 03:05 PM (PDT) @ Grand Ballroom
Feature-Critic Networks for Heterogeneous Domain Generalization
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Room 103
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Room 201
Imputing Missing Events in Continuous-Time Event Streams
In
Time Series
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Room 104
DeepMDP: Learning Continuous Latent Space Models for Representation Learning
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Seaside Ballroom
Regularization in directable environments with application to Tetris
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Grand Ballroom
Learning to Convolve: A Generalized Weight-Tying Approach
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Room 101
A Kernel Theory of Modern Data Augmentation
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Room 102
Homomorphic Sensing
Oral
Tue Jun 11 03:05 PM -- 03:10 PM (PDT) @ Hall A
Non-Parametric Priors For Generative Adversarial Networks
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Room 201
Understanding and Controlling Memory in Recurrent Neural Networks
In
Time Series
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Room 102
Phaseless PCA: Low-Rank Matrix Recovery from Column-wise Phaseless Measurements
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Room 101
kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Room 103
Safe Grid Search with Optimal Complexity
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Grand Ballroom
On Dropout and Nuclear Norm Regularization
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Seaside Ballroom
Improved Dynamic Graph Learning through Fault-Tolerant Sparsification
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Room 104
Importance Sampling Policy Evaluation with an Estimated Behavior Policy
Oral
Tue Jun 11 03:10 PM -- 03:15 PM (PDT) @ Hall A
Lipschitz Generative Adversarial Nets
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Hall A
HexaGAN: Generative Adversarial Nets for Real World Classification
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Room 103
SAGA with Arbitrary Sampling
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Room 102
Rate Distortion For Model Compression:From Theory To Practice
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Seaside Ballroom
Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Room 101
Scalable Learning in Reproducing Kernel Krein Spaces
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Grand Ballroom
Gradient Descent Finds Global Minima of Deep Neural Networks
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Room 201
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
In
Time Series
Oral
Tue Jun 11 03:15 PM -- 03:20 PM (PDT) @ Room 104
Learning from a Learner
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Room 104
Separable value functions across time-scales
[
Video]
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Room 201
Subspace Robust Wasserstein Distances
In
General ML
[
Video]
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Room 103
Natural Analysts in Adaptive Data Analysis
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Seaside Ballroom
Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff
[
Video]
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Room 101
Dirichlet Simplex Nest and Geometric Inference
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Grand Ballroom
Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Hall A
Graph Matching Networks for Learning the Similarity of Graph Structured Objects
Oral
Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Hall B
An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Seaside Ballroom
Collaborative Channel Pruning for Deep Networks
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Room 103
CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Hall B
Differentiable Linearized ADMM
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Room 101
Bayesian leave-one-out cross-validation for large data
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Hall A
BayesNAS: A Bayesian Approach for Neural Architecture Search
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Room 104
Learning Action Representations for Reinforcement Learning
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Grand Ballroom
Sublinear Time Nearest Neighbor Search over Generalized Weighted Space
Oral
Tue Jun 11 04:20 PM -- 04:25 PM (PDT) @ Room 201
Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models
In
General ML
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Room 101
Rao-Blackwellized Stochastic Gradients for Discrete Distributions
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Seaside Ballroom
Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Hall A
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Grand Ballroom
Compressing Gradient Optimizers via Count-Sketches
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Room 103
Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Hall B
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Room 201
Active Manifolds: A non-linear analogue to Active Subspaces
In
General ML
Oral
Tue Jun 11 04:25 PM -- 04:30 PM (PDT) @ Room 104
Bayesian Counterfactual Risk Minimization
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Hall B
A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Room 101
Neurally-Guided Structure Inference
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Grand Ballroom
Scalable Fair Clustering
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Room 201
Optimal Minimal Margin Maximization with Boosting
In
General ML
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Room 104
Per-Decision Option Discounting
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Seaside Ballroom
GDPP: Learning Diverse Generations using Determinantal Point Processes
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Room 103
Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
Oral
Tue Jun 11 04:30 PM -- 04:35 PM (PDT) @ Hall A
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Hall B
The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Seaside Ballroom
Co-Representation Network for Generalized Zero-Shot Learning
[
Slides]
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Room 104
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Room 103
Optimality Implies Kernel Sum Classifiers are Statistically Efficient
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Grand Ballroom
Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Room 101
Bayesian Joint Spike-and-Slab Graphical Lasso
Oral
Tue Jun 11 04:35 PM -- 04:40 PM (PDT) @ Hall A
Graph U-Nets
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Room 104
A Theory of Regularized Markov Decision Processes
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Hall A
SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Room 103
The Implicit Fairness Criterion of Unconstrained Learning
[
Video]
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Room 101
Rotation Invariant Householder Parameterization for Bayesian PCA
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Hall B
AdaGrad stepsizes: sharp convergence over nonconvex landscapes
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Grand Ballroom
Fault Tolerance in Iterative-Convergent Machine Learning
[
Video]
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Seaside Ballroom
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Oral
Tue Jun 11 04:40 PM -- 05:00 PM (PDT) @ Room 201
Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
In
General ML
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Grand Ballroom
Static Automatic Batching In TensorFlow
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Room 104
Discovering Options for Exploration by Minimizing Cover Time
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Hall B
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Room 101
A Framework for Bayesian Optimization in Embedded Subspaces
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Hall A
Area Attention
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Room 201
Variational Inference for sparse network reconstruction from count data
In
General ML
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Seaside Ballroom
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Oral
Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Room 103
Weak Detection of Signal in the Spiked Wigner Model
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Hall B
SWALP : Stochastic Weight Averaging in Low Precision Training
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Grand Ballroom
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Room 104
Policy Certificates: Towards Accountable Reinforcement Learning
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Room 103
Rademacher Complexity for Adversarially Robust Generalization
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Seaside Ballroom
Geometry Aware Convolutional Filters for Omnidirectional Images Representation
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Room 201
Simplifying Graph Convolutional Networks
In
General ML
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Room 101
Convolutional Poisson Gamma Belief Network
Oral
Tue Jun 11 05:05 PM -- 05:10 PM (PDT) @ Hall A
The Evolved Transformer
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Room 101
Automatic Posterior Transformation for Likelihood-Free Inference
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Room 103
Provably efficient RL with Rich Observations via Latent State Decoding
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Hall A
Jumpout : Improved Dropout for Deep Neural Networks with ReLUs
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Grand Ballroom
Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Hall B
Efficient optimization of loops and limits with randomized telescoping sums
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Seaside Ballroom
A Personalized Affective Memory Model for Improving Emotion Recognition
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Room 104
Action Robust Reinforcement Learning and Applications in Continuous Control
Oral
Tue Jun 11 05:10 PM -- 05:15 PM (PDT) @ Room 201
Robust Influence Maximization for Hyperparametric Models
In
General ML
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Seaside Ballroom
Temporal Gaussian Mixture Layer for Videos
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Hall B
Self-similar Epochs: Value in arrangement
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Room 103
Information-Theoretic Considerations in Batch Reinforcement Learning
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Room 104
The Value Function Polytope in Reinforcement Learning
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Hall A
Stochastic Deep Networks
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Room 201
HyperGAN: A Generative Model for Diverse, Performant Neural Networks
In
General ML
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Room 101
Active Learning for Decision-Making from Imbalanced Observational Data
Oral
Tue Jun 11 05:15 PM -- 05:20 PM (PDT) @ Grand Ballroom
DL2: Training and Querying Neural Networks with Logic
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Room 101
Distribution calibration for regression
[
Video]
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Room 201
Exploiting Worker Correlation for Label Aggregation in Crowdsourcing
In
Applications
[
Video]
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Grand Ballroom
Theoretically Principled Trade-off between Robustness and Accuracy
[
Video]
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Room 102
On the Convergence and Robustness of Adversarial Training
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Seaside Ballroom
Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards
[
Video]
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Room 103
Distributed Learning with Sublinear Communication
In
Optimization
[
Video]
Oral
Wed Jun 12 11:00 AM -- 11:20 AM (PDT) @ Room 104
Complexity of Linear Regions in Deep Networks
[
Video]
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Room 103
On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization
In
Optimization
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Hall A
FloWaveNet : A Generative Flow for Raw Audio
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Room 104
On Connected Sublevel Sets in Deep Learning
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Room 101
Graph Convolutional Gaussian Processes
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Room 102
Learning with Bad Training Data via Iterative Trimmed Loss Minimization
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Room 201
Efficient Amortised Bayesian Inference for Hierarchical and Nonlinear Dynamical Systems
In
Applications
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Seaside Ballroom
Target Tracking for Contextual Bandits: Application to Demand Side Management
Oral
Wed Jun 12 11:20 AM -- 11:25 AM (PDT) @ Grand Ballroom
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Seaside Ballroom
Correlated bandits or: How to minimize mean-squared error online
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Room 103
Stochastic Gradient Push for Distributed Deep Learning
In
Optimization
[
Slides]
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Grand Ballroom
ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Room 101
Asynchronous Batch Bayesian Optimisation with Improved Local Penalisation
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Room 102
On discriminative learning of prediction uncertainty
[
Slides]
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Room 201
A Multitask Multiple Kernel Learning Algorithm for Survival Analysis with Application to Cancer Biology
In
Applications
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Room 104
Adversarial Examples Are a Natural Consequence of Test Error in Noise
Oral
Wed Jun 12 11:25 AM -- 11:30 AM (PDT) @ Hall A
Are Generative Classifiers More Robust to Adversarial Attacks?
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Hall A
A Gradual, Semi-Discrete Approach to Generative Network Training via Explicit Wasserstein Minimization
[
Slides]
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Room 201
Fast and Flexible Inference of Joint Distributions from their Marginals
In
Applications
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Room 102
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Room 101
GOODE: A Gaussian Off-The-Shelf Ordinary Differential Equation Solver
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Room 103
Collective Model Fusion for Multiple Black-Box Experts
In
Optimization
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Seaside Ballroom
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Room 104
Greedy Layerwise Learning Can Scale To ImageNet
Oral
Wed Jun 12 11:30 AM -- 11:35 AM (PDT) @ Grand Ballroom
Certified Adversarial Robustness via Randomized Smoothing
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Room 103
Trading Redundancy for Communication: Speeding up Distributed SGD for Non-convex Optimization
In
Optimization
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Hall A
Disentangling Disentanglement in Variational Autoencoders
[
Slides]
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Room 102
Does Data Augmentation Lead to Positive Margin?
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Room 101
Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Room 104
On the Impact of the Activation function on Deep Neural Networks Training
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Seaside Ballroom
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Grand Ballroom
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Oral
Wed Jun 12 11:35 AM -- 11:40 AM (PDT) @ Room 201
Cognitive model priors for predicting human decisions
In
Applications
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Hall A
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Room 201
Conditioning by adaptive sampling for robust design
In
Applications
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Room 101
AReS and MaRS - Adversarial and MMD-Minimizing Regression for SDEs
[
Video]
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Grand Ballroom
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
[
Video]
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Seaside Ballroom
Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Room 103
Trimming the $\ell_1$ Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning
In
Optimization
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Room 102
Robust Learning from Untrusted Sources
Oral
Wed Jun 12 11:40 AM -- 12:00 PM (PDT) @ Room 104
Estimating Information Flow in Deep Neural Networks
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Room 104
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Seaside Ballroom
Bilinear Bandits with Low-rank Structure
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Room 102
SELFIE: Refurbishing Unclean Samples for Robust Deep Learning
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Hall A
A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
[
Slides]
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Room 103
Compressed Factorization: Fast and Accurate Low-Rank Factorization of Compressively-Sensed Data
In
Optimization
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Room 201
Direct Uncertainty Prediction for Medical Second Opinions
In
Applications
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Grand Ballroom
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
Oral
Wed Jun 12 12:00 PM -- 12:05 PM (PDT) @ Room 101
End-to-End Probabilistic Inference for Nonstationary Audio Analysis
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Room 101
Deep Gaussian Processes with Importance-Weighted Variational Inference
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Room 201
Dynamic Measurement Scheduling for Event Forecasting using Deep RL
In
Applications
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Room 103
Noisy Dual Principal Component Pursuit
In
Optimization
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Hall A
Emerging Convolutions for Generative Normalizing Flows
[
Slides]
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Grand Ballroom
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Room 104
Characterizing Well-Behaved vs. Pathological Deep Neural Networks
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Seaside Ballroom
Online Learning to Rank with Features
[
Slides]
Oral
Wed Jun 12 12:05 PM -- 12:10 PM (PDT) @ Room 102
Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Room 103
Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
In
Optimization
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Hall A
A Large-Scale Study on Regularization and Normalization in GANs
[
Slides]
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Room 201
Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization
In
Applications
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Grand Ballroom
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Seaside Ballroom
On the Design of Estimators for Bandit Off-Policy Evaluation
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Room 104
Understanding Geometry of Encoder-Decoder CNNs
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Room 101
Automated Model Selection with Bayesian Quadrature
Oral
Wed Jun 12 12:10 PM -- 12:15 PM (PDT) @ Room 102
Concentration Inequalities for Conditional Value at Risk
[
Slides]
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Room 104
Traditional and Heavy Tailed Self Regularization in Neural Network Models
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Room 201
DeepNose: Using artificial neural networks to represent the space of odorants
In
Applications
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Hall A
Variational Annealing of GANs: A Langevin Perspective
[
Slides]
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Seaside Ballroom
Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Grand Ballroom
Simple Black-box Adversarial Attacks
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Room 102
Data Poisoning Attacks in Multi-Party Learning
Oral
Wed Jun 12 12:15 PM -- 12:20 PM (PDT) @ Room 103
Screening rules for Lasso with non-convex Sparse Regularizers
In
Optimization
Oral
Wed Jun 12 02:00 PM -- 02:20 PM (PDT) @ Seaside Ballroom
Context-Aware Zero-Shot Learning for Object Recognition
[
Video]
Oral
Wed Jun 12 02:00 PM -- 02:20 PM (PDT) @ Room 103
Monge blunts Bayes: Hardness Results for Adversarial Training
Oral
Wed Jun 12 02:00 PM -- 02:20 PM (PDT) @ Room 101
Beyond the Chinese Restaurant and Pitman-Yor processes: Statistical Models with double power-law behavior
[
Video]
Oral
Wed Jun 12 02:00 PM -- 02:20 PM (PDT) @ Room 102
Distributed Weighted Matching via Randomized Composable Coresets
[
Slides]
Oral
Wed Jun 12 02:00 PM -- 02:20 PM (PDT) @ Room 201
Domain Agnostic Learning with Disentangled Representations
[
Video]
Oral
Wed Jun 12 02:00 PM -- 02:20 PM (PDT) @ Room 104
Almost surely constrained convex optimization
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Room 101
DP-GP-LVM: A Bayesian Non-Parametric Model for Learning Multivariate Dependency Structures
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Seaside Ballroom
Band-limited Training and Inference for Convolutional Neural Networks
[
Slides]
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Room 104
Generalized Majorization-Minimization
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Room 201
Composing Value Functions in Reinforcement Learning
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Hall A
NAS-Bench-101: Towards Reproducible Neural Architecture Search
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Room 103
Better generalization with less data using robust gradient descent
Oral
Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Room 102
Multivariate Submodular Optimization
[
Slides]
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Room 102
Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio
[
Slides]
[
Spotlight Slides]
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Room 104
On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Room 101
Random Function Priors for Correlation Modeling
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Hall A
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Room 201
Fast Context Adaptation via Meta-Learning
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Room 103
Near optimal finite time identification of arbitrary linear dynamical systems
Oral
Wed Jun 12 02:25 PM -- 02:30 PM (PDT) @ Seaside Ballroom
Learning Classifiers for Target Domain with Limited or No Labels
[
Slides]
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Room 101
Variational Russian Roulette for Deep Bayesian Nonparametrics
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Room 103
Lossless or Quantized Boosting with Integer Arithmetic
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Hall A
LegoNet: Efficient Convolutional Neural Networks with Lego Filters
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Room 104
Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Room 201
Provable Guarantees for Gradient-Based Meta-Learning
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Seaside Ballroom
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
Oral
Wed Jun 12 02:30 PM -- 02:35 PM (PDT) @ Room 102
Approximating Orthogonal Matrices with Effective Givens Factorization
[
Slides]
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Room 201
Towards Understanding Knowledge Distillation
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Hall A
Sorting Out Lipschitz Function Approximation
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Room 103
Orthogonal Random Forest for Causal Inference
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Seaside Ballroom
Anomaly Detection With Multiple-Hypotheses Predictions
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Room 102
New results on information theoretic clustering
[
Slides]
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Room 101
Incorporating Grouping Information into Bayesian Decision Tree Ensembles
Oral
Wed Jun 12 02:35 PM -- 02:40 PM (PDT) @ Room 104
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
Oral
Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Seaside Ballroom
Kernel Mean Matching for Content Addressability of GANs
[
Video]
Oral
Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Room 104
Efficient Dictionary Learning with Gradient Descent
[
Video]
Oral
Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Room 201
Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers
Oral
Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Room 102
Improved Parallel Algorithms for Density-Based Network Clustering
[
Slides]
Oral
Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Hall A
Graph Element Networks: adaptive, structured computation and memory
Oral
Wed Jun 12 02:40 PM -- 03:00 PM (PDT) @ Room 103
MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means
[
Video]
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Room 103
The advantages of multiple classes for reducing overfitting from test set reuse
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Seaside Ballroom
Neural Inverse Knitting: From Images to Manufacturing Instructions
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Room 104
Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Room 101
Discovering Latent Covariance Structures for Multiple Time Series
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Hall A
Training CNNs with Selective Allocation of Channels
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Room 201
Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation
Oral
Wed Jun 12 03:00 PM -- 03:05 PM (PDT) @ Room 102
Submodular Observation Selection and Information Gathering for Quadratic Models
[
Slides]
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Hall A
Equivariant Transformer Networks
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Room 101
Scalable Training of Inference Networks for Gaussian-Process Models
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Room 103
On the statistical rate of nonlinear recovery in generative models with heavy-tailed data
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Room 102
Submodular Cost Submodular Cover with an Approximate Oracle
[
Slides]
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Room 201
Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Hall B
Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN
In
Deep RL
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Room 104
Riemannian adaptive stochastic gradient algorithms on matrix manifolds
Oral
Wed Jun 12 03:05 PM -- 03:10 PM (PDT) @ Seaside Ballroom
Making Convolutional Networks Shift-Invariant Again
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Room 103
Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Hall A
Overcoming Multi-model Forgetting
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Room 104
Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Room 102
Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity
[
Slides]
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Room 101
Bayesian Optimization Meets Bayesian Optimal Stopping
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Seaside Ballroom
Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation
[
Slides]
Oral
Wed Jun 12 03:10 PM -- 03:15 PM (PDT) @ Room 201
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
Oral
Wed Jun 12 03:15 PM -- 03:20 PM (PDT) @ Room 101
Learning interpretable continuous-time models of latent stochastic dynamical systems
Oral
Wed Jun 12 03:15 PM -- 03:20 PM (PDT) @ Room 104
Alternating Minimizations Converge to Second-Order Optimal Solutions
Oral
Wed Jun 12 03:15 PM -- 03:20 PM (PDT) @ Seaside Ballroom
IMEXnet - A Forward Stable Deep Neural Network
Oral
Wed Jun 12 03:15 PM -- 03:20 PM (PDT) @ Room 103
On Medians of (Randomized) Pairwise Means
Oral
Wed Jun 12 03:15 PM -- 03:20 PM (PDT) @ Room 201
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
Oral
Wed Jun 12 03:15 PM -- 03:20 PM (PDT) @ Hall A
Bayesian Nonparametric Federated Learning of Neural Networks
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Room 103
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances
[
Video]
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Room 201
Active Embedding Search via Noisy Paired Comparisons
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Room 104
Provably Efficient Imitation Learning from Observation Alone
[
Video]
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Hall B
Tensor Variable Elimination for Plated Factor Graphs
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Seaside Ballroom
Do ImageNet Classifiers Generalize to ImageNet?
[
Video]
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Room 101
A Tree-Based Method for Fast Repeated Sampling of Determinantal Point Processes
[
Video]
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Grand Ballroom
Adversarially Learned Representations for Information Obfuscation and Inference
Oral
Wed Jun 12 04:00 PM -- 04:20 PM (PDT) @ Hall A
How does Disagreement Help Generalization against Label Corruption?
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Hall A
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Room 102
Detecting Overlapping and Correlated Communities without Pure Nodes: Identifiability and Algorithm
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Room 201
Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Grand Ballroom
Adaptive Neural Trees
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Room 103
SGD without Replacement: Sharper Rates for General Smooth Convex Functions
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Room 104
Dead-ends and Secure Exploration in Reinforcement Learning
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Seaside Ballroom
Exploring the Landscape of Spatial Robustness
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Hall B
Predicate Exchange: Inference with Declarative Knowledge
Oral
Wed Jun 12 04:20 PM -- 04:25 PM (PDT) @ Room 101
Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Room 103
On the Complexity of Approximating Wasserstein Barycenters
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Hall A
Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Room 102
Learning Generative Models across Incomparable Spaces
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Room 104
Statistics and Samples in Distributional Reinforcement Learning
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Grand Ballroom
Connectivity-Optimized Representation Learning via Persistent Homology
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Room 201
Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Seaside Ballroom
Sever: A Robust Meta-Algorithm for Stochastic Optimization
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Hall B
Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography
Oral
Wed Jun 12 04:25 PM -- 04:30 PM (PDT) @ Room 101
Understanding and Accelerating Particle-Based Variational Inference
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Room 104
Hessian Aided Policy Gradient
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Hall A
Deep Compressed Sensing
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Hall B
Hierarchical Decompositional Mixtures of Variational Autoencoders
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Room 103
Estimate Sequences for Variance-Reduced Stochastic Composite Optimization
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Room 101
Efficient learning of smooth probability functions from Bernoulli tests with guarantees
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Grand Ballroom
Minimal Achievable Sufficient Statistic Learning
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Room 201
Bayesian Generative Active Deep Learning
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Seaside Ballroom
Analyzing Federated Learning through an Adversarial Lens
Oral
Wed Jun 12 04:30 PM -- 04:35 PM (PDT) @ Room 102
Relational Pooling for Graph Representations
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Room 201
Active Learning for Probabilistic Structured Prediction of Cuts and Matchings
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Room 103
A Dynamical Systems Perspective on Nesterov Acceleration
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Seaside Ballroom
Fairwashing: the risk of rationalization
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Hall B
Finding Mixed Nash Equilibria of Generative Adversarial Networks
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Hall A
Differentiable Dynamic Normalization for Learning Deep Representation
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Room 101
The Variational Predictive Natural Gradient
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Room 102
Disentangled Graph Convolutional Networks
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Grand Ballroom
Learning to Route in Similarity Graphs
Oral
Wed Jun 12 04:35 PM -- 04:40 PM (PDT) @ Room 104
Provably Efficient Maximum Entropy Exploration
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Grand Ballroom
Invariant-Equivariant Representation Learning for Multi-Class Data
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Room 101
Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Hall A
Toward Understanding the Importance of Noise in Training Neural Networks
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Room 201
Active Learning with Disagreement Graphs
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Room 103
Random Shuffling Beats SGD after Finite Epochs
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Room 102
Open Vocabulary Learning on Source Code with a Graph-Structured Cache
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Hall B
CompILE: Compositional Imitation Learning and Execution
[
Video]
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Room 104
Combining parametric and nonparametric models for off-policy evaluation
Oral
Wed Jun 12 04:40 PM -- 05:00 PM (PDT) @ Seaside Ballroom
Understanding the Origins of Bias in Word Embeddings
[
Video]
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Hall B
Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Hall A
Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Room 201
Multi-Frequency Vector Diffusion Maps
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Room 104
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Room 103
First-Order Algorithms Converge Faster than $O(1/k)$ on Convex Problems
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Grand Ballroom
Infinite Mixture Prototypes for Few-shot Learning
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Room 102
Learning Discrete Structures for Graph Neural Networks
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Room 101
An Instability in Variational Inference for Topic Models
Oral
Wed Jun 12 05:00 PM -- 05:05 PM (PDT) @ Seaside Ballroom
Bias Also Matters: Bias Attribution for Deep Neural Network Explanation
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Grand Ballroom
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Room 104
Transfer of Samples in Policy Search via Multiple Importance Sampling
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Room 103
Improved Convergence for $\ell_1$ and $\ell_\infty$ Regression via Iteratively Reweighted Least Squares
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Room 102
Compositional Fairness Constraints for Graph Embeddings
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Room 201
Co-manifold learning with missing data
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Hall A
Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Seaside Ballroom
Interpreting Adversarially Trained Convolutional Neural Networks
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Room 101
Bayesian Optimization of Composite Functions
Oral
Wed Jun 12 05:05 PM -- 05:10 PM (PDT) @ Hall B
Deep Generative Learning via Variational Gradient Flow
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Room 103
Optimal Mini-Batch and Step Sizes for SAGA
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Seaside Ballroom
Counterfactual Visual Explanations
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Hall A
Understanding the Impact of Entropy on Policy Optimization
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Grand Ballroom
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Room 102
A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Hall B
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Room 104
Exploration Conscious Reinforcement Learning Revisited
Oral
Wed Jun 12 05:10 PM -- 05:15 PM (PDT) @ Room 101
The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Seaside Ballroom
Data Poisoning Attacks on Stochastic Bandits
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Room 103
Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Hall A
Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Room 104
Kernel-Based Reinforcement Learning in Robust Markov Decision Processes
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Room 102
Stochastic Blockmodels meet Graph Neural Networks
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Room 101
Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization
Oral
Wed Jun 12 05:15 PM -- 05:20 PM (PDT) @ Hall B
Learning Neurosymbolic Generative Models via Program Synthesis
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Room 201
Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random
In
Applications
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Room 101
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
[
Oral]
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Room 104
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
[
Oral]
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Hall B
Batch Policy Learning under Constraints
[
Slides]
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Hall A
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
[
Slides]
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Seaside Ballroom
On Sparse Linear Regression in the Local Differential Privacy Model
[
Oral]
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Room 102
Matrix-Free Preconditioning in Online Learning
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Grand Ballroom
Neural Network Attributions: A Causal Perspective
Oral
Thu Jun 13 09:00 AM -- 09:20 AM (PDT) @ Room 103
Geometric Losses for Distributional Learning
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Hall B
Quantifying Generalization in Reinforcement Learning
[
Slides]
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Room 102
Online Convex Optimization in Adversarial Markov Decision Processes
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Room 201
Linear-Complexity Data-Parallel Earth Mover's Distance Approximations
In
Applications
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Room 103
Classification from Positive, Unlabeled and Biased Negative Data
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Room 101
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Seaside Ballroom
Differentially Private Empirical Risk Minimization with Non-convex Loss Functions
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Room 104
Stochastic Iterative Hard Thresholding for Graph-structured Sparsity Optimization
Oral
Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Grand Ballroom
Towards a Deep and Unified Understanding of Deep Neural Models in NLP
[
Slides]
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Room 101
Unifying Orthogonal Monte Carlo Methods
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Room 104
Neuron birth-death dynamics accelerates gradient descent and converges asymptotically
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Hall A
Latent Normalizing Flows for Discrete Sequences
[
Slides]
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Room 201
Model Comparison for Semantic Grouping
In
Applications
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Room 102
Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games
[
Slides]
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Seaside Ballroom
Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Grand Ballroom
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation
[
Slides]
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Room 103
Complementary-Label Learning for Arbitrary Losses and Models
Oral
Thu Jun 13 09:25 AM -- 09:30 AM (PDT) @ Hall B
Learning Latent Dynamics for Planning from Pixels
[
Slides]
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Grand Ballroom
Functional Transparency for Structured Data: a Game-Theoretic Approach
[
Slides]
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Hall A
Multi-objective training of Generative Adversarial Networks with multiple discriminators
[
Slides]
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Room 102
Online Learning with Sleeping Experts and Feedback Graphs
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Room 201
RaFM: Rank-Aware Factorization Machines
In
Applications
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Hall B
Projections for Approximate Policy Iteration Algorithms
[
Slides]
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Seaside Ballroom
Differentially Private Learning of Geometric Concepts
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Room 104
Width Provably Matters in Optimization for Deep Linear Neural Networks
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Room 103
Learning to Infer Program Sketches
Oral
Thu Jun 13 09:30 AM -- 09:35 AM (PDT) @ Room 101
Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Room 201
CAB: Continuous Adaptive Blending for Policy Evaluation and Learning
In
Applications
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Room 102
Incremental Randomized Sketching for Online Kernel Learning
[
Slides]
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Room 104
Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Room 101
Metropolis-Hastings Generative Adversarial Networks
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Seaside Ballroom
Toward Controlling Discrimination in Online Ad Auctions
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Grand Ballroom
Exploring interpretable LSTM neural networks over multi-variable data
[
Slides]
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Room 103
Hierarchically Structured Meta-learning
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Hall A
Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
[
Slides]
Oral
Thu Jun 13 09:35 AM -- 09:40 AM (PDT) @ Hall B
Learning Structured Decision Problems with Unawareness
[
Slides]
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Hall A
Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Room 101
Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Room 201
MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
In
Applications
[
Oral]
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Room 102
Adaptive Scale-Invariant Online Algorithms for Learning Linear Models
[
Oral]
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Room 103
Bridging Theory and Algorithm for Domain Adaptation
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Hall B
Calibrated Model-Based Deep Reinforcement Learning
[
Slides]
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Grand Ballroom
TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Room 104
Power k-Means Clustering
Oral
Thu Jun 13 09:40 AM -- 10:00 AM (PDT) @ Seaside Ballroom
Learning Optimal Fair Policies
[
Oral]
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Hall B
Reinforcement Learning in Configurable Continuous Environments
[
Slides]
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Room 201
Neural Separation of Observed and Unobserved Distributions
In
Applications
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Seaside Ballroom
Fairness-Aware Learning for Continuous Attributes and Treatments
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Hall A
Graphite: Iterative Generative Modeling of Graphs
[
Slides]
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Room 102
Online Control with Adversarial Disturbances
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Room 101
Replica Conditional Sequential Monte Carlo
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Room 104
Distributed Learning over Unreliable Networks
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Room 103
Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
Oral
Thu Jun 13 10:00 AM -- 10:05 AM (PDT) @ Grand Ballroom
Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute
[
Slides]
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Grand Ballroom
State-Regularized Recurrent Neural Networks
[
Slides]
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Hall A
Hybrid Models with Deep and Invertible Features
[
Slides]
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Room 102
Adversarial Online Learning with noise
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Room 103
Learning What and Where to Transfer
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Seaside Ballroom
Fairness risk measures
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Room 101
A Polynomial Time MCMC Method for Sampling from Continuous Determinantal Point Processes
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Room 201
Almost Unsupervised Text to Speech and Automatic Speech Recognition
In
Applications
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Hall B
Target-Based Temporal-Difference Learning
[
Slides]
Oral
Thu Jun 13 10:05 AM -- 10:10 AM (PDT) @ Room 104
Escaping Saddle Points with Adaptive Gradient Methods
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Room 101
Adaptive Antithetic Sampling for Variance Reduction
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Grand Ballroom
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
[
Slides]
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Room 104
$\texttt{DoubleSqueeze}$: Parallel Stochastic Gradient Descent with Double-pass Error-Compensated Compression
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Hall A
MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets
[
Slides]
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Room 102
Online Variance Reduction with Mixtures
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Room 201
AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
In
Applications
Oral
Thu Jun 13 10:10 AM -- 10:15 AM (PDT) @ Hall B
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
[
Slides]
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Grand Ballroom
On the Connection Between Adversarial Robustness and Saliency Map Interpretability
[
Slides]
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Room 104
Model Function Based Conditional Gradient Method with Armijo-like Line Search
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Room 201
A fully differentiable beam search decoder
In
Applications
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Room 101
Accelerated Flow for Probability Distributions
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Hall A
On Scalable and Efficient Computation of Large Scale Optimal Transport
[
Slides]
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Room 102
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
Oral
Thu Jun 13 10:15 AM -- 10:20 AM (PDT) @ Hall B
Finding Options that Minimize Planning Time
[
Slides]
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Room 201
Scaling Up Ordinal Embedding: A Landmark Approach
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Hall B
Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement
[
Slides]
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Hall A
Understanding and correcting pathologies in the training of learned optimizers
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Room 104
Analogies Explained: Towards Understanding Word Embeddings
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Room 102
Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Room 103
DBSCAN++: Towards fast and scalable density clustering
[
Oral]
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Grand Ballroom
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
[
Oral]
Oral
Thu Jun 13 11:00 AM -- 11:20 AM (PDT) @ Room 101
Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Room 201
Learning to select for a predefined ranking
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Room 102
Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Room 101
Dimensionality Reduction for Tukey Regression
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Room 104
Parameter-Efficient Transfer Learning for NLP
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Grand Ballroom
On the Spectral Bias of Neural Networks
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Room 103
Concrete Autoencoders: Differentiable Feature Selection and Reconstruction
Oral
Thu Jun 13 11:20 AM -- 11:25 AM (PDT) @ Hall B
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
[
Slides]
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Grand Ballroom
Recursive Sketches for Modular Deep Learning
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Room 102
Adaptive Regret of Convex and Smooth Functions
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Room 104
Efficient On-Device Models using Neural Projections
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Room 201
Mallows ranking models: maximum likelihood estimate and regeneration
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Room 101
Efficient Full-Matrix Adaptive Regularization
Oral
Thu Jun 13 11:25 AM -- 11:30 AM (PDT) @ Room 103
Gromov-Wasserstein Learning for Graph Matching and Node Embedding
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Room 201
Fast and Stable Maximum Likelihood Estimation for Incomplete Multinomial Models
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Room 103
Spectral Clustering of Signed Graphs via Matrix Power Means
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Room 104
Deep Residual Output Layers for Neural Language Generation
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Room 102
Online Adaptive Principal Component Analysis and Its extensions
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Hall B
CoT: Cooperative Training for Generative Modeling of Discrete Data
[
Slides]
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Hall A
Unreproducible Research is Reproducible
[
Slides]
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Room 101
Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms
Oral
Thu Jun 13 11:30 AM -- 11:35 AM (PDT) @ Grand Ballroom
Zero-Shot Knowledge Distillation in Deep Networks
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Room 201
Fast Algorithm for Generalized Multinomial Models with Ranking Data
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Hall A
Geometric Scattering for Graph Data Analysis
[
Slides]
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Room 104
Improving Neural Language Modeling via Adversarial Training
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Grand Ballroom
A Convergence Theory for Deep Learning via Over-Parameterization
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Hall B
Non-Monotonic Sequential Text Generation
[
Slides]
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Room 101
Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Room 102
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction
Oral
Thu Jun 13 11:35 AM -- 11:40 AM (PDT) @ Room 103
Coresets for Ordered Weighted Clustering
[
Slides]
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Hall B
Insertion Transformer: Flexible Sequence Generation via Insertion Operations
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Room 103
Fair k-Center Clustering for Data Summarization
[
Oral]
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Room 101
Robust Estimation of Tree Structured Gaussian Graphical Models
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Hall A
Robust Inference via Generative Classifiers for Handling Noisy Labels
[
Slides]
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Grand Ballroom
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
[
Oral]
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Room 104
Mixture Models for Diverse Machine Translation: Tricks of the Trade
[
Oral]
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Room 102
Anytime Online-to-Batch, Optimism and Acceleration
Oral
Thu Jun 13 11:40 AM -- 12:00 PM (PDT) @ Room 201
Graph Resistance and Learning from Pairwise Comparisons
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Room 103
A Better k-means++ Algorithm via Local Search
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Grand Ballroom
Approximation and non-parametric estimation of ResNet-type convolutional neural networks
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Room 102
Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Hall B
Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models
[
Slides]
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Room 201
Learning Context-dependent Label Permutations for Multi-label Classification
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Room 101
Spectral Approximate Inference
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Hall A
LIT: Learned Intermediate Representation Training for Model Compression
[
Slides]
Oral
Thu Jun 13 12:00 PM -- 12:05 PM (PDT) @ Room 104
MASS: Masked Sequence to Sequence Pre-training for Language Generation
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Room 104
Humor in Word Embeddings: Cockamamie Gobbledegook for Nincompoops
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Grand Ballroom
Global Convergence of Block Coordinate Descent in Deep Learning
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Room 102
Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Room 101
Partially Linear Additive Gaussian Graphical Models
[
Slides]
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Room 201
Discovering Context Effects from Raw Choice Data
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Room 103
Kernel Normalized Cut: a Theoretical Revisit
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Hall B
Trainable Decoding of Sets of Sequences for Neural Sequence Models
[
Slides]
Oral
Thu Jun 13 12:05 PM -- 12:10 PM (PDT) @ Hall A
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss
[
Slides]
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Hall B
Learning to Generalize from Sparse and Underspecified Rewards
[
Slides]
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Hall A
What is the Effect of Importance Weighting in Deep Learning?
[
Slides]
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Room 201
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Room 103
Guarantees for Spectral Clustering with Fairness Constraints
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Grand Ballroom
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Room 102
Adaptive Sensor Placement for Continuous Spaces
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Room 101
DAG-GNN: DAG Structure Learning with Graph Neural Networks
Oral
Thu Jun 13 12:10 PM -- 12:15 PM (PDT) @ Room 104
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Room 201
Learning Distance for Sequences by Learning a Ground Metric
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Grand Ballroom
On the Limitations of Representing Functions on Sets
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Room 104
CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Hall B
Efficient Training of BERT by Progressively Stacking
[
Slides]
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Hall A
Similarity of Neural Network Representations Revisited
[
Slides]
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Room 102
Scale-free adaptive planning for deterministic dynamics & discounted rewards
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Room 101
Random Walks on Hypergraphs with Edge-Dependent Vertex Weights
Oral
Thu Jun 13 12:15 PM -- 12:20 PM (PDT) @ Room 103
Supervised Hierarchical Clustering with Exponential Linkage
Oral
Thu Jun 13 03:00 PM -- 03:20 PM (PDT) @ Hall A #0
Rates of Convergence for Sparse Variational Gaussian Process Regression
Oral
Thu Jun 13 04:00 PM -- 04:20 PM (PDT) @ Grand Ballroom
Probabilistic Neural Symbolic Models for Interpretable Visual Question Answering
Oral
Thu Jun 13 04:00 PM -- 04:20 PM (PDT) @ Hall B
Decentralized Exploration in Multi-Armed Bandits
[
Slides]
Oral
Thu Jun 13 04:00 PM -- 04:20 PM (PDT) @ Seaside Ballroom
Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications
In
Optimization
[
Oral]
Oral
Thu Jun 13 04:00 PM -- 04:20 PM (PDT) @ Room 102
Communication-Constrained Inference and the Role of Shared Randomness
[
Slides]
Oral
Thu Jun 13 04:00 PM -- 04:20 PM (PDT) @ Room 104
COMIC: Multi-view Clustering Without Parameter Selection
[
Oral]
Oral
Thu Jun 13 04:00 PM -- 04:20 PM (PDT) @ Hall A
Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations
Oral
Thu Jun 13 04:20 PM -- 04:25 PM (PDT) @ Room 102
Learning and Data Selection in Big Datasets
[
Slides]
Oral
Thu Jun 13 04:20 PM -- 04:25 PM (PDT) @ Room 104
The Wasserstein Transform
Oral
Thu Jun 13 04:20 PM -- 04:25 PM (PDT) @ Hall A
Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
[
Slides]
Oral
Thu Jun 13 04:20 PM -- 04:25 PM (PDT) @ Seaside Ballroom
Online Algorithms for Rent-Or-Buy with Expert Advice
In
Optimization
Oral
Thu Jun 13 04:20 PM -- 04:25 PM (PDT) @ Grand Ballroom
Nonparametric Bayesian Deep Networks with Local Competition
[
Slides]
[
Spotlight Slides]
Oral
Thu Jun 13 04:20 PM -- 04:25 PM (PDT) @ Hall B
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
[
Slides]
Oral
Thu Jun 13 04:25 PM -- 04:30 PM (PDT) @ Hall A
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities
[
Slides]
Oral
Thu Jun 13 04:25 PM -- 04:30 PM (PDT) @ Grand Ballroom
Good Initializations of Variational Bayes for Deep Models
[
Slides]
Oral
Thu Jun 13 04:25 PM -- 04:30 PM (PDT) @ Room 102
Sublinear quantum algorithms for training linear and kernel-based classifiers
[
Slides]
Oral
Thu Jun 13 04:25 PM -- 04:30 PM (PDT) @ Room 104
Sequential Facility Location: Approximate Submodularity and Greedy Algorithm
Oral
Thu Jun 13 04:25 PM -- 04:30 PM (PDT) @ Hall B
Exploiting structure of uncertainty for efficient matroid semi-bandits
[
Slides]
Oral
Thu Jun 13 04:25 PM -- 04:30 PM (PDT) @ Seaside Ballroom
Non-monotone Submodular Maximization with Nearly Optimal Adaptivity and Query Complexity
In
Optimization
Oral
Thu Jun 13 04:30 PM -- 04:35 PM (PDT) @ Room 104
Neural Collaborative Subspace Clustering
Oral
Thu Jun 13 04:30 PM -- 04:35 PM (PDT) @ Hall A
Multi-Object Representation Learning with Iterative Variational Inference
[
Slides]
Oral
Thu Jun 13 04:30 PM -- 04:35 PM (PDT) @ Grand Ballroom
Dropout as a Structured Shrinkage Prior
[
Slides]
Oral
Thu Jun 13 04:30 PM -- 04:35 PM (PDT) @ Hall B
PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits
[
Slides]
Oral
Thu Jun 13 04:30 PM -- 04:35 PM (PDT) @ Seaside Ballroom
Categorical Feature Compression via Submodular Optimization
In
Optimization
Oral
Thu Jun 13 04:35 PM -- 04:40 PM (PDT) @ Hall A
Cross-Domain 3D Equivariant Image Embeddings
[
Slides]
Oral
Thu Jun 13 04:35 PM -- 04:40 PM (PDT) @ Grand Ballroom
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
[
Slides]
Oral
Thu Jun 13 04:35 PM -- 04:40 PM (PDT) @ Seaside Ballroom
Multi-Frequency Phase Synchronization
In
Optimization
Oral
Thu Jun 13 04:35 PM -- 04:40 PM (PDT) @ Room 104
Unsupervised Deep Learning by Neighbourhood Discovery
Oral
Thu Jun 13 04:35 PM -- 04:40 PM (PDT) @ Hall B
Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model
[
Slides]
Oral
Thu Jun 13 04:35 PM -- 04:40 PM (PDT) @ Room 102
Discovering Conditionally Salient Features with Statistical Guarantees
[
Slides]
Oral
Thu Jun 13 04:40 PM -- 05:00 PM (PDT) @ Hall A
Loss Landscapes of Regularized Linear Autoencoders
[
Slides]
Oral
Thu Jun 13 04:40 PM -- 05:00 PM (PDT) @ Grand Ballroom
On Variational Bounds of Mutual Information
Oral
Thu Jun 13 04:40 PM -- 05:00 PM (PDT) @ Seaside Ballroom
Faster Algorithms for Binary Matrix Factorization
In
Optimization
[
Oral]
Oral
Thu Jun 13 04:40 PM -- 05:00 PM (PDT) @ Room 102
A Theoretical Analysis of Contrastive Unsupervised Representation Learning
Oral
Thu Jun 13 04:40 PM -- 05:00 PM (PDT) @ Hall B
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
Oral
Thu Jun 13 05:00 PM -- 05:05 PM (PDT) @ Room 104
Greedy Orthogonal Pivoting Algorithm for Non-Negative Matrix Factorization
Oral
Thu Jun 13 05:00 PM -- 05:05 PM (PDT) @ Hall A
Hyperbolic Disk Embeddings for Directed Acyclic Graphs
[
Slides]
Oral
Thu Jun 13 05:00 PM -- 05:05 PM (PDT) @ Room 102
The information-theoretic value of unlabeled data in semi-supervised learning
[
Slides]
Oral
Thu Jun 13 05:00 PM -- 05:05 PM (PDT) @ Grand Ballroom
Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation
[
Slides]
Oral
Thu Jun 13 05:00 PM -- 05:05 PM (PDT) @ Hall B
TarMAC: Targeted Multi-Agent Communication
[
Slides]
Oral
Thu Jun 13 05:05 PM -- 05:10 PM (PDT) @ Room 102
Unsupervised Label Noise Modeling and Loss Correction
[
Slides]
Oral
Thu Jun 13 05:05 PM -- 05:10 PM (PDT) @ Room 104
Noise2Self: Blind Denoising by Self-Supervision
Oral
Thu Jun 13 05:05 PM -- 05:10 PM (PDT) @ Grand Ballroom
Hierarchical Importance Weighted Autoencoders
[
Slides]
Oral
Thu Jun 13 05:05 PM -- 05:10 PM (PDT) @ Hall A
LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
[
Slides]
Oral
Thu Jun 13 05:05 PM -- 05:10 PM (PDT) @ Hall B
QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
[
Slides]
Oral
Thu Jun 13 05:05 PM -- 05:10 PM (PDT) @ Seaside Ballroom
Guided evolutionary strategies: augmenting random search with surrogate gradients
In
Optimization
Oral
Thu Jun 13 05:10 PM -- 05:15 PM (PDT) @ Room 104
Learning Dependency Structures for Weak Supervision Models
Oral
Thu Jun 13 05:10 PM -- 05:15 PM (PDT) @ Hall A
Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness
[
Slides]
Oral
Thu Jun 13 05:10 PM -- 05:15 PM (PDT) @ Seaside Ballroom
Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces
In
Optimization
Oral
Thu Jun 13 05:10 PM -- 05:15 PM (PDT) @ Grand Ballroom
Faster Attend-Infer-Repeat with Tractable Probabilistic Models
[
Slides]
Oral
Thu Jun 13 05:10 PM -- 05:15 PM (PDT) @ Room 102
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
[
Slides]
Oral
Thu Jun 13 05:10 PM -- 05:15 PM (PDT) @ Hall B
Actor-Attention-Critic for Multi-Agent Reinforcement Learning
[
Slides]
Oral
Thu Jun 13 05:15 PM -- 05:20 PM (PDT) @ Hall A
Lorentzian Distance Learning for Hyperbolic Representations
[
Slides]
Oral
Thu Jun 13 05:15 PM -- 05:20 PM (PDT) @ Room 104
Geometry and Symmetry in Short-and-Sparse Deconvolution
Oral
Thu Jun 13 05:15 PM -- 05:20 PM (PDT) @ Seaside Ballroom
Semi-Cyclic Stochastic Gradient Descent
In
Optimization
Oral
Thu Jun 13 05:15 PM -- 05:20 PM (PDT) @ Room 102
Pareto Optimal Streaming Unsupervised Classification
[
Slides]
Oral
Thu Jun 13 05:15 PM -- 05:20 PM (PDT) @ Grand Ballroom
Understanding Priors in Bayesian Neural Networks at the Unit Level
[
Slides]
Oral
Thu Jun 13 05:15 PM -- 05:20 PM (PDT) @ Hall B
Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning
[
Slides]