Toggle Poster Visibility
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ Victoria
DiCE: The Infinitely Differentiable Monte Carlo Estimator
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A7
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
[
PDF]
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A6
Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A1
Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A5
Predict and Constrain: Modeling Cardinality in Deep Structured Prediction
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A3
Transfer Learning via Learning to Transfer
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ K1 + K2
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A9
Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ K11
Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory
In
Clustering 1
Oral
Wed Jul 11 02:00 AM -- 02:20 AM (PDT) @ A4
Crowdsourcing with Arbitrary Adversaries
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ K11
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift
In
Clustering 1
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ A7
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
[
PDF]
Oral
Wed Jul 11 02:20 AM -- 02:40 AM (PDT) @ A3
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ A1
Learning with Abandonment
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ A9
Distributed Nonparametric Regression under Communication Constraints
[
PDF]
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ Victoria
Learning to search with MCTSnets
Oral
Wed Jul 11 02:20 AM -- 02:40 AM (PDT) @ A5
SparseMAP: Differentiable Sparse Structured Inference
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ K1 + K2
Nonoverlap-Promoting Variable Selection
Oral
Wed Jul 11 02:20 AM -- 02:30 AM (PDT) @ A4
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model
[
PDF]
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ K1 + K2
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ A1
Lipschitz Continuity in Model-based Reinforcement Learning
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ A4
Conditional Noise-Contrastive Estimation of Unnormalised Models
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ A9
Coded Sparse Matrix Multiplication
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ Victoria
Differentiable plasticity: training plastic neural networks with backpropagation
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ K11
Hierarchical Clustering with Structural Constraints
In
Clustering 1
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ A6
LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration
Oral
Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ A7
Tree Edit Distance Learning via Adaptive Symbol Embeddings
[
PDF]
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A3
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A7
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
[
PDF]
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A5
Efficient and Consistent Adversarial Bipartite Matching
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A6
Variational Network Inference: Strong and Stable with Concrete Support
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ K1 + K2
Black Box FDR
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ Victoria
TACO: Learning Task Decomposition via Temporal Alignment for Control
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ K11
K-means clustering using random matrix sparsification
In
Clustering 1
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A4
Deep One-Class Classification
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A1
Implicit Quantile Networks for Distributional Reinforcement Learning
Oral
Wed Jul 11 02:40 AM -- 02:50 AM (PDT) @ A9
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A5
Learning to Speed Up Structured Output Prediction
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A3
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back
[
PDF]
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A1
More Robust Doubly Robust Off-policy Evaluation
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A9
Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ Victoria
Graph Networks as Learnable Physics Engines for Inference and Control
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ K1 + K2
Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ K11
Clustering Semi-Random Mixtures of Gaussians
In
Clustering 1
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A6
Network Global Testing by Counting Graphlets
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A4
Deep Density Destructors
Oral
Wed Jul 11 02:50 AM -- 03:00 AM (PDT) @ A7
CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions
[
PDF]
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A1
Coordinated Exploration in Concurrent Reinforcement Learning
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A6
Data-Dependent Stability of Stochastic Gradient Descent
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ K11
Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A5
WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A9
Asynchronous Decentralized Parallel Stochastic Gradient Descent
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ K1 + K2
Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A4
Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ Victoria
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A3
Stagewise Safe Bayesian Optimization with Gaussian Processes
[
PDF]
Oral
Wed Jul 11 04:30 AM -- 04:50 AM (PDT) @ A7
Improving Optimization in Models With Continuous Symmetry Breaking
[
PDF]
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ A9
signSGD: Compressed Optimisation for Non-Convex Problems
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ K1 + K2
Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ Victoria
Semi-Supervised Learning via Compact Latent Space Clustering
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ A6
Stability and Generalization of Learning Algorithms that Converge to Global Optima
Oral
Wed Jul 11 04:50 AM -- 05:00 AM (PDT) @ A1
Structured Evolution with Compact Architectures for Scalable Policy Optimization
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ K11
Subspace Embedding and Linear Regression with Orlicz Norm
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ A3
BOCK : Bayesian Optimization with Cylindrical Kernels
[
PDF]
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ A5
Nearly Optimal Robust Subspace Tracking
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ A4
Bayesian Quadrature for Multiple Related Integrals
Oral
Wed Jul 11 04:50 AM -- 05:10 AM (PDT) @ A7
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks
[
PDF]
Oral
Wed Jul 11 05:00 AM -- 05:10 AM (PDT) @ A1
Spotlight: Optimizing Device Placement for Training Deep Neural Networks
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ K1 + K2
An Estimation and Analysis Framework for the Rasch Model
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A5
Safe Element Screening for Submodular Function Minimization
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A4
Differentiable Compositional Kernel Learning for Gaussian Processes
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ K11
Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ Victoria
Conditional Neural Processes
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A7
Learning Steady-States of Iterative Algorithms over Graphs
[
PDF]
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A6
Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A1
Gated Path Planning Networks
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A3
BOHB: Robust and Efficient Hyperparameter Optimization at Scale
[
PDF]
Oral
Wed Jul 11 05:10 AM -- 05:20 AM (PDT) @ A9
Katyusha X: Simple Momentum Method for Stochastic Sum-of-Nonconvex Optimization
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ A1
Best Arm Identification in Linear Bandits with Linear Dimension Dependency
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ A5
Online Convolutional Sparse Coding with Sample-Dependent Dictionary
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ K1 + K2
End-to-end Active Object Tracking via Reinforcement Learning
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ K11
Streaming Principal Component Analysis in Noisy Setting
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ A3
Bayesian Optimization of Combinatorial Structures
[
PDF]
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ Victoria
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ A4
Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ A9
$D^2$: Decentralized Training over Decentralized Data
Oral
Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ A6
Dropout Training, Data-dependent Regularization, and Generalization Bounds
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A5
The Limits of Maxing, Ranking, and Preference Learning
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A4
Variational Inference and Model Selection with Generalized Evidence Bounds
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ K11
Linear Spectral Estimators and an Application to Phase Retrieval
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A1
Structured Control Nets for Deep Reinforcement Learning
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ K1 + K2
Deep Predictive Coding Network for Object Recognition
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A9
An Alternative View: When Does SGD Escape Local Minima?
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A3
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches
[
PDF]
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A6
Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization
[
PDF]
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ Victoria
Non-linear motor control by local learning in spiking neural networks
Oral
Wed Jul 11 05:30 AM -- 05:50 AM (PDT) @ A7
Generative Temporal Models with Spatial Memory for Partially Observed Environments
[
PDF]
Oral
Wed Jul 11 05:50 AM -- 06:10 AM (PDT) @ A3
Selecting Representative Examples for Program Synthesis
[
PDF]
Oral
Wed Jul 11 05:50 AM -- 06:00 AM (PDT) @ K1 + K2
Gradually Updated Neural Networks for Large-Scale Image Recognition
Oral
Wed Jul 11 05:50 AM -- 06:10 AM (PDT) @ A1
Latent Space Policies for Hierarchical Reinforcement Learning
Oral
Wed Jul 11 05:50 AM -- 06:10 AM (PDT) @ A9
Escaping Saddles with Stochastic Gradients
Oral
Wed Jul 11 05:50 AM -- 06:00 AM (PDT) @ A5
Learning a Mixture of Two Multinomial Logits
Oral
Wed Jul 11 05:50 AM -- 06:00 AM (PDT) @ A6
The Generalization Error of Dictionary Learning with Moreau Envelopes
Oral
Wed Jul 11 05:50 AM -- 06:10 AM (PDT) @ A4
Fixing a Broken ELBO
Oral
Wed Jul 11 05:50 AM -- 06:00 AM (PDT) @ Victoria
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
Oral
Wed Jul 11 05:50 AM -- 06:10 AM (PDT) @ K11
Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization
Oral
Wed Jul 11 06:00 AM -- 06:10 AM (PDT) @ A6
On Learning Sparsely Used Dictionaries from Incomplete Samples
Oral
Wed Jul 11 06:00 AM -- 06:10 AM (PDT) @ K1 + K2
Neural Inverse Rendering for General Reflectance Photometric Stereo
Oral
Wed Jul 11 06:00 AM -- 06:10 AM (PDT) @ Victoria
Hierarchical Long-term Video Prediction without Supervision
Oral
Wed Jul 11 06:00 AM -- 06:10 AM (PDT) @ A7
Discovering Interpretable Representations for Both Deep Generative and Discriminative Models
[
PDF]
Oral
Wed Jul 11 06:00 AM -- 06:10 AM (PDT) @ A5
The Weighted Kendall and High-order Kernels for Permutations
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ A4
Tighter Variational Bounds are Not Necessarily Better
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ A1
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ A9
Stochastic Variance-Reduced Cubic Regularized Newton Method
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ A5
Parameterized Algorithms for the Matrix Completion Problem
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ K11
Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ A3
On the Relationship between Data Efficiency and Error for Uncertainty Sampling
[
PDF]
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ A6
The Well-Tempered Lasso
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ K1 + K2
One-Shot Segmentation in Clutter
Oral
Wed Jul 11 06:10 AM -- 06:20 AM (PDT) @ Victoria
Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ A7
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
[
PDF]
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ K1 + K2
Active Testing: An Efficient and Robust Framework for Estimating Accuracy
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ A4
Continuous-Time Flows for Efficient Inference and Density Estimation
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ A9
Non-convex Conditional Gradient Sliding
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ K11
Testing Sparsity over Known and Unknown Bases
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ A1
An Inference-Based Policy Gradient Method for Learning Options
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ A6
Differentially Private Identity and Equivalence Testing of Discrete Distributions
Oral
Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ Victoria
Model-Level Dual Learning
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A5
Stochastic Training of Graph Convolutional Networks with Variance Reduction
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A6
Differentially Private Matrix Completion Revisited
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A7
Which Training Methods for GANs do actually Converge?
[
PDF]
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A9
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A4
Semi-Implicit Variational Inference
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ K1 + K2
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A1
Programmatically Interpretable Reinforcement Learning
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ A3
Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
[
PDF]
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ Victoria
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
Oral
Wed Jul 11 07:00 AM -- 07:20 AM (PDT) @ K11
Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?
Oral
Wed Jul 11 07:20 AM -- 07:30 AM (PDT) @ Victoria
Orthogonal Recurrent Neural Networks with Scaled Cayley Transform
Oral
Wed Jul 11 07:20 AM -- 07:40 AM (PDT) @ K1 + K2
The Dynamics of Learning: A Random Matrix Approach
Oral
Wed Jul 11 07:20 AM -- 07:30 AM (PDT) @ A6
Mitigating Bias in Adaptive Data Gathering via Differential Privacy
Oral
Wed Jul 11 07:20 AM -- 07:30 AM (PDT) @ A9
Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees
Oral
Wed Jul 11 07:20 AM -- 07:40 AM (PDT) @ A5
Representation Learning on Graphs with Jumping Knowledge Networks
Oral
Wed Jul 11 07:20 AM -- 07:40 AM (PDT) @ K11
Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams
Oral
Wed Jul 11 07:20 AM -- 07:40 AM (PDT) @ A4
Efficient Gradient-Free Variational Inference using Policy Search
Oral
Wed Jul 11 07:20 AM -- 07:40 AM (PDT) @ A3
Feedback-Based Tree Search for Reinforcement Learning
[
PDF]
Oral
Wed Jul 11 07:20 AM -- 07:40 AM (PDT) @ A1
Learning by Playing - Solving Sparse Reward Tasks from Scratch
Oral
Wed Jul 11 07:30 AM -- 07:40 AM (PDT) @ A9
ADMM and Accelerated ADMM as Continuous Dynamical Systems
[
PDF]
Oral
Wed Jul 11 07:30 AM -- 07:40 AM (PDT) @ Victoria
Kronecker Recurrent Units
Oral
Wed Jul 11 07:30 AM -- 07:40 AM (PDT) @ A6
Local Private Hypothesis Testing: Chi-Square Tests
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A9
Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A3
Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
[
PDF]
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ K11
Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ K1 + K2
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A6
Locally Private Hypothesis Testing
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A1
Automatic Goal Generation for Reinforcement Learning Agents
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A7
Learning Implicit Generative Models with the Method of Learned Moments
[
PDF]
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A4
A Spectral Approach to Gradient Estimation for Implicit Distributions
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ A5
Learning Diffusion using Hyperparameters
Oral
Wed Jul 11 07:40 AM -- 07:50 AM (PDT) @ Victoria
Fast Parametric Learning with Activation Memorization
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A6
INSPECTRE: Privately Estimating the Unseen
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ Victoria
Dynamic Evaluation of Neural Sequence Models
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A7
A Classification-Based Study of Covariate Shift in GAN Distributions
[
PDF]
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A5
Canonical Tensor Decomposition for Knowledge Base Completion
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A4
Quasi-Monte Carlo Variational Inference
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ K1 + K2
Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A1
Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A9
An Efficient Semismooth Newton based Algorithm for Convex Clustering
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ A3
Learning the Reward Function for a Misspecified Model
[
PDF]
Oral
Wed Jul 11 07:50 AM -- 08:00 AM (PDT) @ K11
Data Summarization at Scale: A Two-Stage Submodular Approach
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ A1
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ A6
Delayed Impact of Fair Machine Learning
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ Victoria
Decoupled Parallel Backpropagation with Convergence Guarantee
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ K1 + K2
Essentially No Barriers in Neural Network Energy Landscape
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ A5
Dependent Relational Gamma Process Models for Longitudinal Networks
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ K11
Learning to Optimize Combinatorial Functions
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ A9
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ A4
Yes, but Did It Work?: Evaluating Variational Inference
Oral
Wed Jul 11 08:00 AM -- 08:20 AM (PDT) @ A7
Differentiable Abstract Interpretation for Provably Robust Neural Networks
[
PDF]
Oral
Wed Jul 11 08:20 AM -- 08:30 AM (PDT) @ K11
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A6
Fairness Without Demographics in Repeated Loss Minimization
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ Victoria
Efficient Neural Architecture Search via Parameters Sharing
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A1
Path Consistency Learning in Tsallis Entropy Regularized MDPs
Oral
Wed Jul 11 08:20 AM -- 08:30 AM (PDT) @ K1 + K2
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A4
Augment and Reduce: Stochastic Inference for Large Categorical Distributions
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A7
Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope
[
PDF]
Oral
Wed Jul 11 08:20 AM -- 08:30 AM (PDT) @ A9
Fast Variance Reduction Method with Stochastic Batch Size
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A5
NetGAN: Generating Graphs via Random Walks
Oral
Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A3
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
[
PDF]
Oral
Wed Jul 11 08:30 AM -- 08:40 AM (PDT) @ K1 + K2
Not All Samples Are Created Equal: Deep Learning with Importance Sampling
Oral
Wed Jul 11 08:30 AM -- 08:40 AM (PDT) @ A9
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
Oral
Wed Jul 11 08:30 AM -- 08:40 AM (PDT) @ K11
Binary Partitions with Approximate Minimum Impurity
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ A3
Been There, Done That: Meta-Learning with Episodic Recall
[
PDF]
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ A4
Black-Box Variational Inference for Stochastic Differential Equations
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ A5
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ A1
Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ A6
Nonconvex Optimization for Regression with Fairness Constraints
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ K11
Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ A9
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ K1 + K2
Learning Deep ResNet Blocks Sequentially using Boosting Theory
Oral
Wed Jul 11 08:40 AM -- 08:50 AM (PDT) @ Victoria
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A5
Neural Relational Inference for Interacting Systems
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A4
Inference Suboptimality in Variational Autoencoders
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A3
Continual Reinforcement Learning with Complex Synapses
[
PDF]
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ Victoria
Spline Filters For End-to-End Deep Learning
[
PDF]
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A1
Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A6
Fair and Diverse DPP-Based Data Summarization
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ K1 + K2
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A9
A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ A7
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
[
PDF]
Oral
Wed Jul 11 08:50 AM -- 09:00 AM (PDT) @ K11
Bounds on the Approximation Power of Feedforward Neural Networks
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A9
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks
[
PDF]
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ K1
Learning Memory Access Patterns
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A3
Learning Policy Representations in Multiagent Systems
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A1
Convergent Tree Backup and Retrace with Function Approximation
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ Victoria
Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
[
PDF]
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A7
Geometry Score: A Method For Comparing Generative Adversarial Networks
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A6
Multicalibration: Calibration for the (Computationally-Identifiable) Masses
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A5
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ A4
Learning unknown ODE models with Gaussian processes
Oral
Thu Jul 12 02:00 AM -- 02:20 AM (PDT) @ K11
Probabilistic Boolean Tensor Decomposition
Oral
Thu Jul 12 02:20 AM -- 02:40 AM (PDT) @ K1
Geodesic Convolutional Shape Optimization
Oral
Thu Jul 12 02:20 AM -- 02:40 AM (PDT) @ A4
Constraining the Dynamics of Deep Probabilistic Models
Oral
Thu Jul 12 02:20 AM -- 02:40 AM (PDT) @ A5
Differentiable Dynamic Programming for Structured Prediction and Attention
Oral
Thu Jul 12 02:20 AM -- 02:40 AM (PDT) @ Victoria
Compressing Neural Networks using the Variational Information Bottelneck
[
PDF]
Oral
Thu Jul 12 02:20 AM -- 02:30 AM (PDT) @ A7
Optimizing the Latent Space of Generative Networks
Oral
Thu Jul 12 02:20 AM -- 02:30 AM (PDT) @ A3
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems
Oral
Thu Jul 12 02:20 AM -- 02:40 AM (PDT) @ A9
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization
[
PDF]
Oral
Thu Jul 12 02:20 AM -- 02:40 AM (PDT) @ A1
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
Oral
Thu Jul 12 02:20 AM -- 02:30 AM (PDT) @ K11
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
Oral
Thu Jul 12 02:20 AM -- 02:30 AM (PDT) @ A6
Residual Unfairness in Fair Machine Learning from Prejudiced Data
Oral
Thu Jul 12 02:30 AM -- 02:40 AM (PDT) @ A3
Learning to Act in Decentralized Partially Observable MDPs
Oral
Thu Jul 12 02:30 AM -- 02:40 AM (PDT) @ K11
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion
Oral
Thu Jul 12 02:30 AM -- 02:40 AM (PDT) @ A7
Adversarial Learning with Local Coordinate Coding
Oral
Thu Jul 12 02:30 AM -- 02:40 AM (PDT) @ A6
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A9
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding
[
PDF]
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ K1
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ K11
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A5
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A7
Learning Representations and Generative Models for 3D Point Clouds
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A3
Modeling Others using Oneself in Multi-Agent Reinforcement Learning
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A4
Probabilistic Recurrent State-Space Models
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A1
Scalable Bilinear Pi Learning Using State and Action Features
Oral
Thu Jul 12 02:40 AM -- 02:50 AM (PDT) @ A6
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A6
Adversarial Regression with Multiple Learners
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A3
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A4
Structured Variationally Auto-encoded Optimization
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A7
Theoretical Analysis of Image-to-Image Translation with Adversarial Learning
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ K11
Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A5
End-to-End Learning for the Deep Multivariate Probit Model
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A9
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?
[
PDF]
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ Victoria
Deep Models of Interactions Across Sets
[
PDF]
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ K1
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
Oral
Thu Jul 12 02:50 AM -- 03:00 AM (PDT) @ A1
Stochastic Variance-Reduced Policy Gradient
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A7
Composite Functional Gradient Learning of Generative Adversarial Models
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ K1
Learning One Convolutional Layer with Overlapping Patches
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A9
Shampoo: Preconditioned Stochastic Tensor Optimization
[
PDF]
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A3
Fast Information-theoretic Bayesian Optimisation
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A1
Investigating Human Priors for Playing Video Games
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ K11
Improved large-scale graph learning through ridge spectral sparsification
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A5
Accelerated Spectral Ranking
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A6
Inductive Two-Layer Modeling with Parametric Bregman Transfer
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ A4
Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap
Oral
Thu Jul 12 04:30 AM -- 04:50 AM (PDT) @ Victoria
Focused Hierarchical RNNs for Conditional Sequence Processing
[
PDF]
Oral
Thu Jul 12 04:50 AM -- 05:00 AM (PDT) @ A5
Composite Marginal Likelihood Methods for Random Utility Models
Oral
Thu Jul 12 04:50 AM -- 05:00 AM (PDT) @ A9
Characterizing Implicit Bias in Terms of Optimization Geometry
[
PDF]
Oral
Thu Jul 12 04:50 AM -- 05:00 AM (PDT) @ A4
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
Oral
Thu Jul 12 04:50 AM -- 05:10 AM (PDT) @ K11
Parallel and Streaming Algorithms for K-Core Decomposition
Oral
Thu Jul 12 04:50 AM -- 05:00 AM (PDT) @ A6
Does Distributionally Robust Supervised Learning Give Robust Classifiers?
Oral
Thu Jul 12 04:50 AM -- 05:00 AM (PDT) @ A1
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Oral
Thu Jul 12 04:50 AM -- 05:10 AM (PDT) @ A3
Optimization, fast and slow: optimally switching between local and Bayesian optimization
Oral
Thu Jul 12 04:50 AM -- 05:00 AM (PDT) @ A7
Tempered Adversarial Networks
Oral
Thu Jul 12 04:50 AM -- 05:10 AM (PDT) @ K1
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
Oral
Thu Jul 12 04:50 AM -- 05:10 AM (PDT) @ Victoria
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations
[
PDF]
Oral
Thu Jul 12 05:00 AM -- 05:10 AM (PDT) @ A1
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms
Oral
Thu Jul 12 05:00 AM -- 05:10 AM (PDT) @ A4
Stochastic Variance-Reduced Hamilton Monte Carlo Methods
Oral
Thu Jul 12 05:00 AM -- 05:10 AM (PDT) @ A9
A Distributed Second-Order Algorithm You Can Trust
[
PDF]
Oral
Thu Jul 12 05:00 AM -- 05:10 AM (PDT) @ A6
Prediction Rule Reshaping
Oral
Thu Jul 12 05:00 AM -- 05:10 AM (PDT) @ A5
Ranking Distributions based on Noisy Sorting
Oral
Thu Jul 12 05:00 AM -- 05:10 AM (PDT) @ A7
Improved Training of Generative Adversarial Networks Using Representative Features
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A7
A Two-Step Computation of the Exact GAN Wasserstein Distance
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A5
SQL-Rank: A Listwise Approach to Collaborative Ranking
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A4
A Robust Approach to Sequential Information Theoretic Planning
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ K11
Fast Approximate Spectral Clustering for Dynamic Networks
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A6
Finding Influential Training Samples for Gradient Boosted Decision Trees
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A9
A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning
[
PDF]
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ K1
The Multilinear Structure of ReLU Networks
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ Victoria
Learning long term dependencies via Fourier recurrent units
[
PDF]
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A1
Time Limits in Reinforcement Learning
Oral
Thu Jul 12 05:10 AM -- 05:20 AM (PDT) @ A3
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A7
Is Generator Conditioning Causally Related to GAN Performance?
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ Victoria
Training Neural Machines with Trace-Based Supervision
[
PDF]
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A6
Noise2Noise: Learning Image Restoration without Clean Data
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ K11
Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A1
Visualizing and Understanding Atari Agents
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A4
Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A9
Gradient Coding from Cyclic MDS Codes and Expander Graphs
[
PDF]
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ K1
Understanding the Loss Surface of Neural Networks for Binary Classification
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A3
Tight Regret Bounds for Bayesian Optimization in One Dimension
Oral
Thu Jul 12 05:20 AM -- 05:30 AM (PDT) @ A5
Extreme Learning to Rank via Low Rank Assumption
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A5
Feasible Arm Identification
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A7
Black-box Adversarial Attacks with Limited Queries and Information
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ K11
Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A3
To Understand Deep Learning We Need to Understand Kernel Learning
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A4
Robust and Scalable Models of Microbiome Dynamics
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A9
Alternating Randomized Block Coordinate Descent
[
PDF]
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ Victoria
Neural Dynamic Programming for Musical Self Similarity
[
PDF]
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ K1
Tropical Geometry of Deep Neural Networks
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A1
The Mirage of Action-Dependent Baselines in Reinforcement Learning
Oral
Thu Jul 12 05:30 AM -- 05:50 AM (PDT) @ A6
Dimensionality-Driven Learning with Noisy Labels
Oral
Thu Jul 12 05:50 AM -- 06:10 AM (PDT) @ A5
Bandits with Delayed, Aggregated Anonymous Feedback
Oral
Thu Jul 12 05:50 AM -- 06:00 AM (PDT) @ Victoria
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
[
PDF]
Oral
Thu Jul 12 05:50 AM -- 06:10 AM (PDT) @ A7
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
[
PDF]
Oral
Thu Jul 12 05:50 AM -- 06:10 AM (PDT) @ A3
Kernel Recursive ABC: Point Estimation with Intractable Likelihood
Oral
Thu Jul 12 05:50 AM -- 06:10 AM (PDT) @ A1
Smoothed Action Value Functions for Learning Gaussian Policies
Oral
Thu Jul 12 05:50 AM -- 06:00 AM (PDT) @ A6
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
Oral
Thu Jul 12 05:50 AM -- 06:00 AM (PDT) @ A4
Stein Variational Message Passing for Continuous Graphical Models
Oral
Thu Jul 12 05:50 AM -- 06:10 AM (PDT) @ K1
A Spline Theory of Deep Learning
Oral
Thu Jul 12 05:50 AM -- 06:00 AM (PDT) @ K11
Loss Decomposition for Fast Learning in Large Output Spaces
Oral
Thu Jul 12 06:00 AM -- 06:10 AM (PDT) @ K11
Ultra Large-Scale Feature Selection using Count-Sketches
Oral
Thu Jul 12 06:00 AM -- 06:10 AM (PDT) @ A6
Learning to Reweight Examples for Robust Deep Learning
Oral
Thu Jul 12 06:00 AM -- 06:10 AM (PDT) @ Victoria
Fast Decoding in Sequence Models Using Discrete Latent Variables
[
PDF]
Oral
Thu Jul 12 06:00 AM -- 06:10 AM (PDT) @ A4
A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ A3
Differentially Private Database Release via Kernel Mean Embeddings
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ A9
Accelerating Greedy Coordinate Descent Methods
[
PDF]
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ A4
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ K11
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ Victoria
PixelSNAIL: An Improved Autoregressive Generative Model
[
PDF]
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ A5
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ A1
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
[
PDF]
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ A6
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks
Oral
Thu Jul 12 06:10 AM -- 06:20 AM (PDT) @ K1
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A3
Learning in Reproducing Kernel Kreı̆n Spaces
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A5
Thompson Sampling for Combinatorial Semi-Bandits
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A4
Bucket Renormalization for Approximate Inference
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ K11
Semi-Supervised Learning on Data Streams via Temporal Label Propagation
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A7
GAIN: Missing Data Imputation using Generative Adversarial Nets
[
PDF]
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A1
Addressing Function Approximation Error in Actor-Critic Methods
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A9
On Acceleration with Noise-Corrupted Gradients
[
PDF]
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ K1
Stronger Generalization Bounds for Deep Nets via a Compression Approach
Oral
Thu Jul 12 06:20 AM -- 06:30 AM (PDT) @ A6
Improving Regression Performance with Distributional Losses
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ K1
Reviving and Improving Recurrent Back-Propagation
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ A4
Variational Bayesian dropout: pitfalls and fixes
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ A6
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ A9
Approximate message passing for amplitude based optimization
[
PDF]
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ K11
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ Victoria
Using Inherent Structures to design Lean 2-layer RBMs
[
PDF]
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ A3
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ A5
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity
Oral
Thu Jul 12 07:00 AM -- 07:20 AM (PDT) @ A7
The Mechanics of n-Player Differentiable Games
[
PDF]
Oral
Thu Jul 12 07:20 AM -- 07:30 AM (PDT) @ A7
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning
[
PDF]
Oral
Thu Jul 12 07:20 AM -- 07:40 AM (PDT) @ A6
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Oral
Thu Jul 12 07:20 AM -- 07:40 AM (PDT) @ A1
Beyond the One-Step Greedy Approach in Reinforcement Learning
[
PDF]
Oral
Thu Jul 12 07:20 AM -- 07:30 AM (PDT) @ Victoria
Deep Asymmetric Multi-task Feature Learning
[
PDF]
Oral
Thu Jul 12 07:20 AM -- 07:30 AM (PDT) @ K1
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks
Oral
Thu Jul 12 07:20 AM -- 07:40 AM (PDT) @ A5
Practical Contextual Bandits with Regression Oracles
Oral
Thu Jul 12 07:20 AM -- 07:40 AM (PDT) @ A3
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Oral
Thu Jul 12 07:20 AM -- 07:40 AM (PDT) @ A9
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
[
PDF]
Oral
Thu Jul 12 07:20 AM -- 07:30 AM (PDT) @ K11
Approximation Guarantees for Adaptive Sampling
Oral
Thu Jul 12 07:20 AM -- 07:30 AM (PDT) @ A4
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Oral
Thu Jul 12 07:30 AM -- 07:40 AM (PDT) @ Victoria
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
[
PDF]
Oral
Thu Jul 12 07:30 AM -- 07:40 AM (PDT) @ K1
Invariance of Weight Distributions in Rectified MLPs
Oral
Thu Jul 12 07:30 AM -- 07:40 AM (PDT) @ K11
Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions
[
PDF]
Oral
Thu Jul 12 07:30 AM -- 07:40 AM (PDT) @ A4
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ Victoria
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
[
PDF]
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A9
prDeep: Robust Phase Retrieval with a Flexible Deep Network
[
PDF]
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A7
Towards Fast Computation of Certified Robustness for ReLU Networks
[
PDF]
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A6
Functional Gradient Boosting based on Residual Network Perception
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ K1
Learning Dynamics of Linear Denoising Autoencoders
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ K11
Constrained Interacting Submodular Groupings
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A3
Fitting New Speakers Based on a Short Untranscribed Sample
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A1
Policy and Value Transfer in Lifelong Reinforcement Learning
[
PDF]
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A5
Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate
Oral
Thu Jul 12 07:40 AM -- 07:50 AM (PDT) @ A4
Scalable approximate Bayesian inference for particle tracking data
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ K1
Understanding Generalization and Optimization Performance of Deep CNNs
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A1
Importance Weighted Transfer of Samples in Reinforcement Learning
[
PDF]
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A3
Towards Binary-Valued Gates for Robust LSTM Training
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A9
Accelerating Natural Gradient with Higher-Order Invariance
[
PDF]
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A6
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A7
LaVAN: Localized and Visible Adversarial Noise
[
PDF]
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A5
Stochastic Proximal Algorithms for AUC Maximization
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ A4
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ K11
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice
Oral
Thu Jul 12 07:50 AM -- 08:00 AM (PDT) @ Victoria
High Performance Zero-Memory Overhead Direct Convolutions
[
PDF]
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ K11
Representation Tradeoffs for Hyperbolic Embeddings
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ Victoria
ContextNet: Deep learning for Star Galaxy Classification
[
PDF]
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ A5
Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ A3
Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ A6
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ A1
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
[
PDF]
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ K1
Composable Planning with Attributes
Oral
Thu Jul 12 08:00 AM -- 08:20 AM (PDT) @ A7
Synthesizing Programs for Images using Reinforced Adversarial Learning
[
PDF]
Oral
Thu Jul 12 08:20 AM -- 08:30 AM (PDT) @ A4
Distilling the Posterior in Bayesian Neural Networks
Oral
Thu Jul 12 08:20 AM -- 08:40 AM (PDT) @ K1
Measuring abstract reasoning in neural networks
Oral
Thu Jul 12 08:20 AM -- 08:30 AM (PDT) @ A9
Learning Compact Neural Networks with Regularization
[
PDF]
Oral
Thu Jul 12 08:20 AM -- 08:30 AM (PDT) @ Victoria
Autoregressive Convolutional Neural Networks for Asynchronous Time Series
[
PDF]
Oral
Thu Jul 12 08:20 AM -- 08:40 AM (PDT) @ A3
Deep Variational Reinforcement Learning for POMDPs
Oral
Thu Jul 12 08:20 AM -- 08:40 AM (PDT) @ K11
Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances
Oral
Thu Jul 12 08:20 AM -- 08:30 AM (PDT) @ A6
Open Category Detection with PAC Guarantees
Oral
Thu Jul 12 08:20 AM -- 08:30 AM (PDT) @ A5
Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ A6
Unbiased Objective Estimation in Predictive Optimization
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ A9
Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis
[
PDF]
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ A4
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ A7
Max-Mahalanobis Linear Discriminant Analysis Networks
[
PDF]
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ Victoria
Hierarchical Multi-Label Classification Networks
[
PDF]
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ A1
Decoupling Gradient-Like Learning Rules from Representations
[
PDF]
Oral
Thu Jul 12 08:30 AM -- 08:40 AM (PDT) @ A5
Self-Bounded Prediction Suffix Tree via Approximate String Matching
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ K1
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ A6
Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ A1
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
[
PDF]
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ A5
Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ K11
Local Density Estimation in High Dimensions
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ A4
Noisy Natural Gradient as Variational Inference
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ A9
Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering
[
PDF]
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ A3
Recurrent Predictive State Policy Networks
Oral
Thu Jul 12 08:40 AM -- 08:50 AM (PDT) @ Victoria
Nonparametric variable importance using an augmented neural network with multi-task learning
[
PDF]
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A9
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation
[
PDF]
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A3
Regret Minimization for Partially Observable Deep Reinforcement Learning
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A1
Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning
[
PDF]
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ K11
Improving Sign Random Projections With Additional Information
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ Victoria
Knowledge Transfer with Jacobian Matching
[
PDF]
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A6
Towards Black-box Iterative Machine Teaching
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A7
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training
[
PDF]
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A5
Learning Localized Spatio-Temporal Models From Streaming Data
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A4
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
[
PDF]
Oral
Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ K1
Explicit Inductive Bias for Transfer Learning with Convolutional Networks
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A9
Convergence guarantees for a class of non-convex and non-smooth optimization problems
[
PDF]
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A1
RLlib: Abstractions for Distributed Reinforcement Learning
[
PDF]
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A3
Learning Registered Point Processes from Idiosyncratic Observations
[
PDF]
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ K11
Out-of-sample extension of graph adjacency spectral embedding
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A5
Dynamic Regret of Strongly Adaptive Methods
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A7
Mixed batches and symmetric discriminators for GAN training
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A4
Learning in Integer Latent Variable Models with Nested Automatic Differentiation
[
PDF]
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ A6
A Reductions Approach to Fair Classification
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ K1
Solving Partial Assignment Problems using Random Clique Complexes
Oral
Fri Jul 13 12:30 AM -- 12:50 AM (PDT) @ Victoria
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
[
PDF]
Oral
Fri Jul 13 12:50 AM -- 01:00 AM (PDT) @ Victoria
Learning equations for extrapolation and control
[
PDF]
Oral
Fri Jul 13 12:50 AM -- 01:00 AM (PDT) @ K1
Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction
Oral
Fri Jul 13 12:50 AM -- 01:00 AM (PDT) @ A4
Sound Abstraction and Decomposition of Probabilistic Programs
[
PDF]
Oral
Fri Jul 13 12:50 AM -- 01:00 AM (PDT) @ A5
Online Learning with Abstention
Oral
Fri Jul 13 12:50 AM -- 01:00 AM (PDT) @ A7
Mutual Information Neural Estimation
Oral
Fri Jul 13 12:50 AM -- 01:10 AM (PDT) @ A6
Probably Approximately Metric-Fair Learning
Oral
Fri Jul 13 12:50 AM -- 01:00 AM (PDT) @ K11
Bayesian Model Selection for Change Point Detection and Clustering
Oral
Fri Jul 13 12:50 AM -- 01:10 AM (PDT) @ A1
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
[
PDF]
Oral
Fri Jul 13 12:50 AM -- 01:10 AM (PDT) @ A9
A Progressive Batching L-BFGS Method for Machine Learning
[
PDF]
Oral
Fri Jul 13 01:00 AM -- 01:10 AM (PDT) @ K11
An Iterative, Sketching-based Framework for Ridge Regression
Oral
Fri Jul 13 01:00 AM -- 01:10 AM (PDT) @ K1
Video Prediction with Appearance and Motion Conditions
Oral
Fri Jul 13 01:00 AM -- 01:10 AM (PDT) @ A7
Adversarially Regularized Autoencoders
Oral
Fri Jul 13 01:00 AM -- 01:10 AM (PDT) @ A5
Multi-Fidelity Black-Box Optimization with Hierarchical Partitions
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A5
Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A4
The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference
[
PDF]
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A6
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
[
PDF]
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A7
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A9
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks
[
PDF]
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A3
Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling
[
PDF]
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ A1
Mix & Match - Agent Curricula for Reinforcement Learning
[
PDF]
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ K1
Neural Program Synthesis from Diverse Demonstration Videos
Oral
Fri Jul 13 01:10 AM -- 01:20 AM (PDT) @ K11
Provable Variable Selection for Streaming Features
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ K11
Learning Low-Dimensional Temporal Representations
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ A4
Temporal Poisson Square Root Graphical Models
[
PDF]
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ Victoria
Weightless: Lossy weight encoding for deep neural network compression
[
PDF]
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ A5
Firing Bandits: Optimizing Crowdfunding
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ A9
Estimation of Markov Chain via Rank-constrained Likelihood
[
PDF]
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ A7
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
Oral
Fri Jul 13 01:20 AM -- 01:30 AM (PDT) @ A6
Blind Justice: Fairness with Encrypted Sensitive Attributes
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ K11
Competitive Caching with Machine Learned Advice
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A3
Learning Adversarially Fair and Transferable Representations
[
PDF]
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A1
Hierarchical Imitation and Reinforcement Learning
[
PDF]
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A4
Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF)
[
PDF]
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A7
Junction Tree Variational Autoencoder for Molecular Graph Generation
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ K1
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A6
Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A9
A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming
[
PDF]
Oral
Fri Jul 13 02:20 AM -- 02:30 AM (PDT) @ A3
Learning Semantic Representations for Unsupervised Domain Adaptation
[
PDF]
Oral
Fri Jul 13 02:20 AM -- 02:40 AM (PDT) @ A7
Semi-Amortized Variational Autoencoders
Oral
Fri Jul 13 02:20 AM -- 02:30 AM (PDT) @ K11
Distributed Clustering via LSH Based Data Partitioning
Oral
Fri Jul 13 02:20 AM -- 02:40 AM (PDT) @ Victoria
Understanding and Simplifying One-Shot Architecture Search
[
PDF]
Oral
Fri Jul 13 02:20 AM -- 02:40 AM (PDT) @ K1
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
Oral
Fri Jul 13 02:20 AM -- 02:40 AM (PDT) @ A4
State Space Gaussian Processes with Non-Gaussian Likelihood
[
PDF]
Oral
Fri Jul 13 02:20 AM -- 02:30 AM (PDT) @ A6
Improved nearest neighbor search using auxiliary information and priority functions
Oral
Fri Jul 13 02:20 AM -- 02:40 AM (PDT) @ A1
Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning
[
PDF]
Oral
Fri Jul 13 02:30 AM -- 02:40 AM (PDT) @ A3
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
[
PDF]
Oral
Fri Jul 13 02:30 AM -- 02:40 AM (PDT) @ K11
Learning to Branch
Oral
Fri Jul 13 02:30 AM -- 02:40 AM (PDT) @ A6
QuantTree: Histograms for Change Detection in Multivariate Data Streams
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ A6
Topological mixture estimation
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ Victoria
Path-Level Network Transformation for Efficient Architecture Search
[
PDF]
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ A3
Rectify Heterogeneous Models with Semantic Mapping
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ A1
State Abstractions for Lifelong Reinforcement Learning
[
PDF]
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ K1
On the Power of Over-parametrization in Neural Networks with Quadratic Activation
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ A5
Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ A7
Iterative Amortized Inference
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ A4
Constant-Time Predictive Distributions for Gaussian Processes
[
PDF]
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ K11
Compiling Combinatorial Prediction Games
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ A6
Revealing Common Statistical Behaviors in Heterogeneous Populations
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ A7
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ A3
Detecting and Correcting for Label Shift with Black Box Predictors
[
PDF]
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ K1
Optimization Landscape and Expressivity of Deep CNNs
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ Victoria
Learning Longer-term Dependencies in RNNs with Auxiliary Losses
[
PDF]
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ K11
Approximation Algorithms for Cascading Prediction Models
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ A5
Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors
[
PDF]
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ A4
Large-Scale Cox Process Inference using Variational Fourier Features
[
PDF]
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ A7
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ K1
Efficient end-to-end learning for quantizable representations
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ A9
SADAGRAD: Strongly Adaptive Stochastic Gradient Methods
[
PDF]
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ K11
On the Spectrum of Random Features Maps of High Dimensional Data
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ A1
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
[
PDF]
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ A3
The Hidden Vulnerability of Distributed Learning in Byzantium
[
PDF]
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ A4
Stein Variational Gradient Descent Without Gradient
[
PDF]
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ Victoria
Progress & Compress: A scalable framework for continual learning
[
PDF]
Oral
Fri Jul 13 07:00 AM -- 07:20 AM (PDT) @ A6
Candidates vs. Noises Estimation for Large Multi-Class Classification Problem
Oral
Fri Jul 13 07:20 AM -- 07:30 AM (PDT) @ A1
Policy Optimization as Wasserstein Gradient Flows
[
PDF]
Oral
Fri Jul 13 07:20 AM -- 07:40 AM (PDT) @ A5
Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions
[
PDF]
Oral
Fri Jul 13 07:20 AM -- 07:40 AM (PDT) @ A4
Minibatch Gibbs Sampling on Large Graphical Models
Oral
Fri Jul 13 07:20 AM -- 07:30 AM (PDT) @ A6
CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning
Oral
Fri Jul 13 07:20 AM -- 07:40 AM (PDT) @ Victoria
Overcoming Catastrophic Forgetting with Hard Attention to the Task
[
PDF]
Oral
Fri Jul 13 07:20 AM -- 07:30 AM (PDT) @ K1
High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach
Oral
Fri Jul 13 07:20 AM -- 07:40 AM (PDT) @ A3
Asynchronous Byzantine Machine Learning (the case of SGD)
[
PDF]
Oral
Fri Jul 13 07:20 AM -- 07:30 AM (PDT) @ A9
Level-Set Methods for Finite-Sum Constrained Convex Optimization
[
PDF]
Oral
Fri Jul 13 07:20 AM -- 07:40 AM (PDT) @ A7
Autoregressive Quantile Networks for Generative Modeling
Oral
Fri Jul 13 07:20 AM -- 07:30 AM (PDT) @ K11
SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions
Oral
Fri Jul 13 07:30 AM -- 07:40 AM (PDT) @ A9
Local Convergence Properties of SAGA/Prox-SVRG and Acceleration
[
PDF]
Oral
Fri Jul 13 07:30 AM -- 07:40 AM (PDT) @ K1
A Boo(n) for Evaluating Architecture Performance
Oral
Fri Jul 13 07:30 AM -- 07:40 AM (PDT) @ A6
Attention-based Deep Multiple Instance Learning
Oral
Fri Jul 13 07:30 AM -- 07:40 AM (PDT) @ K11
Spectrally Approximating Large Graphs with Smaller Graphs
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ A7
Stochastic Video Generation with a Learned Prior
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ A6
Learning and Memorization
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ Victoria
Rapid Adaptation with Conditionally Shifted Neurons
[
PDF]
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ A5
Budgeted Experiment Design for Causal Structure Learning
[
PDF]
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ K11
Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ A9
Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions
[
PDF]
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ A3
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients
[
PDF]
Oral
Fri Jul 13 07:40 AM -- 07:50 AM (PDT) @ K1
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
[
PDF]
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ Victoria
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
[
PDF]
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ A9
Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework
[
PDF]
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ A5
The Hierarchical Adaptive Forgetting Variational Filter
[
PDF]
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ A6
Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ A4
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
[
PDF]
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ K1
On the Limitations of First-Order Approximation in GAN Dynamics
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ A7
Disentangled Sequential Autoencoder
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ A3
Communication-Computation Efficient Gradient Coding
[
PDF]
Oral
Fri Jul 13 07:50 AM -- 08:00 AM (PDT) @ K11
Rates of Convergence of Spectral Methods for Graphon Estimation
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A1
Mean Field Multi-Agent Reinforcement Learning
[
PDF]
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ K11
Convolutional Imputation of Matrix Networks
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ K1
On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A9
Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis
[
PDF]
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A5
Orthogonal Machine Learning: Power and Limitations
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ Victoria
WSNet: Compact and Efficient Networks Through Weight Sampling
[
PDF]
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A4
Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent
[
PDF]
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A3
Analyzing Uncertainty in Neural Machine Translation
[
PDF]
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A7
Modeling Sparse Deviations for Compressed Sensing using Generative Models
Oral
Fri Jul 13 08:00 AM -- 08:20 AM (PDT) @ A6
A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ K11
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
Oral
Fri Jul 13 08:20 AM -- 08:40 AM (PDT) @ Victoria
StrassenNets: Deep Learning with a Multiplication Budget
[
PDF]
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ A7
oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ A4
CRVI: Convex Relaxation for Variational Inference
[
PDF]
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ A6
Classification from Pairwise Similarity and Unlabeled Data
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ K1
Bounding and Counting Linear Regions of Deep Neural Networks
Oral
Fri Jul 13 08:20 AM -- 08:40 AM (PDT) @ A5
Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models
[
PDF]
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ A3
Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks
[
PDF]
Oral
Fri Jul 13 08:20 AM -- 08:40 AM (PDT) @ A1
Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control
[
PDF]
Oral
Fri Jul 13 08:20 AM -- 08:30 AM (PDT) @ A9
Celer: a Fast Solver for the Lasso with Dual Extrapolation
[
PDF]
Oral
Fri Jul 13 08:30 AM -- 08:40 AM (PDT) @ A3
Adaptive Sampled Softmax with Kernel Based Sampling
[
PDF]
Oral
Fri Jul 13 08:30 AM -- 08:40 AM (PDT) @ A6
Comparison-Based Random Forests
Oral
Fri Jul 13 08:30 AM -- 08:40 AM (PDT) @ K11
On the Implicit Bias of Dropout
Oral
Fri Jul 13 08:30 AM -- 08:40 AM (PDT) @ A9
Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation
[
PDF]
Oral
Fri Jul 13 08:30 AM -- 08:40 AM (PDT) @ A7
Noisin: Unbiased Regularization for Recurrent Neural Networks
Oral
Fri Jul 13 08:30 AM -- 08:40 AM (PDT) @ K1
DCFNet: Deep Neural Network with Decomposed Convolutional Filters
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A4
Message Passing Stein Variational Gradient Descent
[
PDF]
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A6
Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ K1
A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A5
Accurate Inference for Adaptive Linear Models
[
PDF]
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ K11
A Unified Framework for Structured Low-rank Matrix Learning
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A9
Efficient First-Order Algorithms for Adaptive Signal Denoising
[
PDF]
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A7
Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ Victoria
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
[
PDF]
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A3
Hierarchical Text Generation and Planning for Strategic Dialogue
[
PDF]
Oral
Fri Jul 13 08:40 AM -- 08:50 AM (PDT) @ A1
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
[
PDF]
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ K11
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ A7
Inter and Intra Topic Structure Learning with Word Embeddings
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ A9
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
[
PDF]
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ A6
Active Learning with Logged Data
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ A1
The Uncertainty Bellman Equation and Exploration
[
PDF]
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ A5
Detecting non-causal artifacts in multivariate linear regression models
[
PDF]
Oral
Fri Jul 13 08:50 AM -- 09:00 AM (PDT) @ A4
Pathwise Derivatives Beyond the Reparameterization Trick
[
PDF]