Theory

On Lower and Upper Bounds in Smooth and Strongly Convex Optimization JMLR 2016 Only H is left: Near-tight Episodic PAC RL NeurIPS 2016 On Searching for Generalized Instrumental Variables AISTATS 2016 On the Expressive Power of Deep Learning: A Tensor Analysis COLT 2016 On the Quality of the Initial Basin in Overspecified Neural Networks ICML 2016 On the Recursive Teaching Dimension of VC Classes NeurIPS 2016 On the Statistical Limits of Convex Relaxations ICML 2016 Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture COLT 2016 Open Problem: Kernel methods on manifolds and metric spaces. What is the probability of a positive definite geodesic exponential kernel? COLT 2016 Open Problem: Property Elicitation and Elicitation Complexity COLT 2016 Open Problem: Second order regret bounds based on scaling time COLT 2016 Orthogonal Random Features NeurIPS 2016 PAC-Bayesian Theory Meets Bayesian Inference NeurIPS 2016 Pareto Front Identification from Stochastic Bandit Feedback AISTATS 2016 Privacy Odometers and Filters: Pay-as-you-Go Composition NeurIPS 2016 Provable Algorithms for Inference in Topic Models ICML 2016 Provably manipulation-resistant reputation systems COLT 2016 Relationship between PreTraining and Maximum Likelihood Estimation in Deep Boltzmann Machines AISTATS 2016 Set-labelled filters and sensor transformations RSS 2016 Should We Really Use Post-Hoc Tests Based on Mean-Ranks? JMLR 2016 Sign rank versus VC dimension COLT 2016 Simple and Scalable Constrained Clustering: a Generalized Spectral Method AISTATS 2016 Simultaneous Clustering and Model Selection for Tensor Affinities CVPR 2016 Solving Marginal MAP Problems with NP Oracles and Parity Constraints NeurIPS 2016 Sparsity and Error Analysis of Empirical Feature-Based Regularization Schemes JMLR 2016