Theory

Exploration of the (Non-)Asymptotic Bias and Variance of Stochastic Gradient Langevin Dynamics JMLR 2016 Exponential expressivity in deep neural networks through transient chaos NeurIPS 2016 Expressiveness of Rectifier Networks ICML 2016 Fairness in Learning: Classic and Contextual Bandits NeurIPS 2016 Fast Collaborative Filtering from Implicit Feedback with Provable Guarantees ACML 2016 Fast methods for estimating the Numerical rank of large matrices ICML 2016 Fast Rate Analysis of Some Stochastic Optimization Algorithms ICML 2016 Full-Capacity Unitary Recurrent Neural Networks NeurIPS 2016 Geometry-aware stationary subspace analysis ACML 2016 Gradient Descent Only Converges to Minimizers COLT 2016 Guarding against Spurious Discoveries in High Dimensions JMLR 2016 How Neural Network Depth Compensates for HMM Conditional Independence Assumptions in DNN-HMM Acoustic Models Interspeech 2016 k-variates++: more pluses in the k-means++ ICML 2016 L1-Regularized Least Squares for Support Recovery of High Dimensional Single Index Models with Gaussian Designs JMLR 2016 Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs NeurIPS 2016 Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences NeurIPS 2016 Local Minimax Complexity of Stochastic Convex Optimization NeurIPS 2016 Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels NeurIPS 2016 Minimax Rates in Permutation Estimation for Feature Matching JMLR 2016 More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning NeurIPS 2016 Multiple-Instance Learning from Distributions JMLR 2016 Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula NeurIPS 2016 Near Optimal Behavior via Approximate State Abstraction ICML 2016 On Bayes Risk Lower Bounds JMLR 2016 Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes NeurIPS 2016