# JMLR Workshop and Conference Proceedings

## Volume 51: Proceedings of the 19th International Conference on Artificial Intelligence and Statistics

**Editors:
Arthur Gretton,
Christian C. Robert
**

### Accepted Papers

Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family Mixtures

[abs] [pdf] [supplementary]

C3: Lightweight Incrementalized MCMC for Probabilistic Programs using Continuations and Callsite Caching

[abs] [pdf] [supplementary]

Probability Inequalities for Kernel Embeddings in Sampling without Replacement

[abs] [pdf] [supplementary]

Sparse Representation of Multivariate Extremes with Applications to Anomaly Ranking

[abs] [pdf] [supplementary]

Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics

[abs] [pdf] [supplementary]

Limits on Sparse Support Recovery via Linear Sketching with Random Expander Matrices

[abs] [pdf] [supplementary]

Maximum Likelihood for Variance Estimation in High-Dimensional Linear Models

[abs] [pdf] [supplementary]

Precision Matrix Estimation in High Dimensional Gaussian Graphical Models with Faster Rates

Computationally Efficient Bayesian Learning of Gaussian Process State Space Models

[abs] [pdf] [supplementary]

Generalized Ideal Parent (GIP): Discovering non-Gaussian Hidden Variables

[abs] [pdf] [supplementary]

On Sparse Variational Methods and the Kullback-Leibler Divergence between Stochastic Processes

Tensor vs. Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations

[abs] [pdf] [supplementary]

Score Permutation Based Finite Sample Inference for Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) Models

Bayes-Optimal Effort Allocation in Crowdsourcing: Bounds and Index Policies

[abs] [pdf] [supplementary]

Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation

A Lasso-based Sparse Knowledge Gradient Policy for Sequential Optimal Learning

[abs] [pdf] [supplementary]

Simple and Scalable Constrained Clustering: a Generalized Spectral Method

[abs] [pdf] [supplementary]

Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree

[abs] [pdf] [supplementary]

Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA

[abs] [pdf] [supplementary]

An Improved Convergence Analysis of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization

[abs] [pdf] [supplementary]

Large-Scale Optimization Algorithms for Sparse Conditional Gaussian Graphical Models

[abs] [pdf] [supplementary]

Relationship between PreTraining and Maximum Likelihood Estimation in Deep Boltzmann Machines

Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization

[abs] [pdf] [supplementary]

On Convergence of Model Parallel Proximal Gradient Algorithm for Stale Synchronous Parallel System

[abs] [pdf] [supplementary]

A Fixed-Point Operator for Inference in Variational Bayesian Latent Gaussian Models

[abs] [pdf] [supplementary]

Learning Probabilistic Submodular Diversity Models Via Noise Contrastive Estimation

[abs] [pdf] [supplementary]

Fast Saddle-Point Algorithm for Generalized Dantzig Selector and FDR Control with Ordered L1-Norm

[abs] [pdf] [supplementary]

High Dimensional Bayesian Optimization via Restricted Projection Pursuit Models

[abs] [pdf] [supplementary]

On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games

[abs] [pdf] [supplementary]

Ordered Weighted L1 Regularized Regression with Strongly Correlated Covariates: Theoretical Aspects

[abs] [pdf] [supplementary]

Exponential Stochastic Cellular Automata for Massively Parallel Inference

[abs] [pdf] [supplementary]

Scalable Gaussian Processes for Characterizing Multidimensional Change Surfaces

[abs] [pdf] [supplementary]

Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization

[abs] [pdf] [supplementary]

Non-negative Matrix Factorization for Discrete Data with Hierarchical Side-Information

[abs] [pdf] [supplementary]

Unwrapping ADMM: Efficient Distributed Computing via Transpose Reduction

[abs] [pdf] [supplementary]

Efficient Bregman Projections onto the Permutahedron and Related Polytopes

[abs] [pdf] [supplementary]

Provable Tensor Methods for Learning Mixtures of Generalized Linear Models

[abs] [pdf] [supplementary]

A Column Generation Bound Minimization Approach with PAC-Bayesian Generalization Guarantees

[abs] [pdf] [supplementary]

Scalable Exemplar Clustering and Facility Location via Augmented Block Coordinate Descent with Column Generation

[abs] [pdf] [supplementary]

On Lloyd’s Algorithm: New Theoretical Insights for Clustering in Practice

[abs] [pdf] [supplementary]

Learning Sigmoid Belief Networks via Monte Carlo Expectation Maximization

[abs] [pdf] [supplementary]

Randomization and The Pernicious Effects of Limited Budgets on Auction Experiments

[abs] [pdf] [supplementary]

Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation

[abs] [pdf] [supplementary]

Online and Distributed Bayesian Moment Matching for Parameter Learning in Sum-Product Networks

Parallel Majorization Minimization with Dynamically Restricted Domains for Nonconvex Optimization

[abs] [pdf] [supplementary]