Theory

Spectral M-estimation with Applications to Hidden Markov Models AISTATS 2016 Structured Prediction Theory Based on Factor Graph Complexity NeurIPS 2016 Supervised learning through the lens of compression NeurIPS 2016 Task-Oriented Intrinsic Evaluation of Semantic Textual Similarity COLING 2016 The Asymptotic Performance of Linear Echo State Neural Networks JMLR 2016 The Effect of Combination Functions on the Complexity of Relational Bayesian Networks PGM 2016 The Optimal Sample Complexity of PAC Learning JMLR 2016 The Parameterized Complexity of Approximate Inference in Bayesian Networks PGM 2016 The Power of Adaptivity in Identifying Statistical Alternatives NeurIPS 2016 The Power of Depth for Feedforward Neural Networks COLT 2016 The Power of Optimization from Samples NeurIPS 2016 Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers NeurIPS 2016 Tractable Operations for Arithmetic Circuits of Probabilistic Models NeurIPS 2016 Universal Approximation Results for the Temporal Restricted Boltzmann Machine and the Recurrent Temporal Restricted Boltzmann Machine JMLR 2016 Unsupervised Risk Estimation Using Only Conditional Independence Structure NeurIPS 2016 What Makes Word-level Neural Machine Translation Hard: A Case Study on English-German Translation COLING 2016 When can we rank well from comparisons of O(n\log(n)) non-actively chosen pairs? COLT 2016 XFT: Practical Fault Tolerance beyond Crashes OSDI 2016 A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data ICML 2015 Algorithmic Stability and Uniform Generalization NeurIPS 2015 An Almost Optimal PAC Algorithm COLT 2015 Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks NeurIPS 2015 A Spectral Algorithm for Inference in Hidden semi-Markov Models AISTATS 2015 Basis refinement strategies for linear value function approximation in MDPs NeurIPS 2015 Beyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering COLT 2015