# JMLR Workshop and Conference Proceedings

## Volume 48: Proceedings of The 33rd International Conference on Machine Learning

**Editors:
Maria Florina Balcan,
Kilian Q. Weinberger
**

### Accepted Papers

No Oops, You Won’t Do It Again: Mechanisms for Self-correction in Crowdsourcing

[abs] [pdf] [supplementary]

Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues

[abs] [pdf] [supplementary]

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

[abs] [pdf] [supplementary]

Additive Approximations in High Dimensional Nonparametric Regression via the SALSA

[abs] [pdf] [supplementary]

CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy

Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity

[abs] [pdf] [supplementary]

Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams

A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression Models

[abs] [pdf] [supplementary]

Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient

[abs] [pdf] [supplementary]

Efficient Private Empirical Risk Minimization for High-dimensional Learning

[abs] [pdf] [supplementary]

Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification

[abs] [pdf] [supplementary]

Loss factorization, weakly supervised learning and label noise robustness

[abs] [pdf] [supplementary]

Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends

[abs] [pdf] [supplementary]

Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms

[abs] [pdf] [supplementary]

PAC Lower Bounds and Efficient Algorithms for The Max \(K\)-Armed Bandit Problem

[abs] [pdf] [supplementary]

A Comparative Analysis and Study of Multiview CNN Models for Joint Object Categorization and Pose Estimation

[abs] [pdf] [supplementary]

BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces

On the Iteration Complexity of Oblivious First-Order Optimization Algorithms

[abs] [pdf] [supplementary]

Anytime Exploration for Multi-armed Bandits using Confidence Information

[abs] [pdf] [supplementary]

Low-rank tensor completion: a Riemannian manifold preconditioning approach

[abs] [pdf] [supplementary]

Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow

[abs] [pdf] [supplementary]

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

[abs] [pdf] [supplementary]

Dirichlet Process Mixture Model for Correcting Technical Variation in Single-Cell Gene Expression Data

[abs] [pdf] [supplementary]

The Knowledge Gradient for Sequential Decision Making with Stochastic Binary Feedbacks

[abs] [pdf] [supplementary]

Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods

[abs] [pdf] [supplementary]

Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks

[abs] [pdf] [supplementary]

A Subspace Learning Approach for High Dimensional Matrix Decomposition with Efficient Column/Row Sampling

Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm

[abs] [pdf] [supplementary]

False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking

[abs] [pdf] [supplementary]

Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

[abs] [pdf] [supplementary]

Fast Constrained Submodular Maximization: Personalized Data Summarization

[abs] [pdf] [supplementary]

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

[abs] [pdf] [supplementary]

Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions

[abs] [pdf] [supplementary]

Deep Gaussian Processes for Regression using Approximate Expectation Propagation

[abs] [pdf] [supplementary]

Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling

[abs] [pdf] [supplementary]

Bounded Off-Policy Evaluation with Missing Data for Course Recommendation and Curriculum Design

[abs] [pdf] [supplementary]

From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

[abs] [pdf] [supplementary]

Gaussian process nonparametric tensor estimator and its minimax optimality

[abs] [pdf] [supplementary]

Matrix Eigen-decomposition via Doubly Stochastic Riemannian Optimization

[abs] [pdf] [supplementary]

ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission

[abs] [pdf] [supplementary]

Fast Parameter Inference in Nonlinear Dynamical Systems using Iterative Gradient Matching

Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors

[abs] [pdf] [supplementary]

Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well

Stochastic Optimization for Multiview Representation Learning using Partial Least Squares

[abs] [pdf] [supplementary]

Differential Geometric Regularization for Supervised Learning of Classifiers

[abs] [pdf] [supplementary]

Barron and Cover’s Theory in Supervised Learning and its Application to Lasso

[abs] [pdf] [supplementary]

Differentially Private Chi-Squared Hypothesis Testing: Goodness of Fit and Independence Testing

[abs] [pdf] [supplementary]

Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization

[abs] [pdf] [supplementary]

Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units

Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference

[abs] [pdf] [supplementary]

A Convex Atomic-Norm Approach to Multiple Sequence Alignment and Motif Discovery

[abs] [pdf] [supplementary]

Efficient Multi-Instance Learning for Activity Recognition from Time Series Data Using an Auto-Regressive Hidden Markov Model

[abs] [pdf] [supplementary]

Generalization Properties and Implicit Regularization for Multiple Passes SGM

[abs] [pdf] [supplementary]

Recovery guarantee of weighted low-rank approximation via alternating minimization

[abs] [pdf] [supplementary]

Square Root Graphical Models: Multivariate Generalizations of Univariate Exponential Families that Permit Positive Dependencies

[abs] [pdf] [supplementary]

Recycling Randomness with Structure for Sublinear time Kernel Expansions

[abs] [pdf] [supplementary]

Faster Convex Optimization: Simulated Annealing with an Efficient Universal Barrier

[abs] [pdf] [supplementary]

A Superlinearly-Convergent Proximal Newton-type Method for the Optimization of Finite Sums

[abs] [pdf] [supplementary]

Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity

Robust Monte Carlo Sampling using Riemannian Nosé-Poincaré Hamiltonian Dynamics

[abs] [pdf] [supplementary]

Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis

[abs] [pdf] [supplementary]

Bayesian Poisson Tucker Decomposition for Learning the Structure of International Relations

[abs] [pdf] [supplementary]

Automatic Construction of Nonparametric Relational Regression Models for Multiple Time Series

[abs] [pdf] [supplementary]

PD-Sparse : A Primal and Dual Sparse Approach to Extreme Multiclass and Multilabel Classification

[abs] [pdf] [supplementary]