Learning Theory

Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits AISTATS 2015 Towards a Learning Theory of Cause-Effect Inference ICML 2015 Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing ICML 2015 Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning AISTATS 2015 Two-stage sampled learning theory on distributions AISTATS 2015 Variable Selection is Hard COLT 2015 A Boosting Framework on Grounds of Online Learning NeurIPS 2014 A Convex Formulation for Mixed Regression with Two Components: Minimax Optimal Rates COLT 2014 Active Learning Using Smooth Relative Regret Approximations with Applications JMLR 2014 Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm ICML 2014 A Finite-Sample Generalization Bound for Semiparametric Regression: Partially Linear Models AISTATS 2014 Altitude Training: Strong Bounds for Single-Layer Dropout NeurIPS 2014 Analysis of Empirical MAP and Empirical Partially Bayes: Can They be Alternatives to Variational Bayes? AISTATS 2014 An Analysis of Active Learning with Uniform Feature Noise AISTATS 2014 An Analysis of State-Relevance Weights and Sampling Distributions on L1-Regularized Approximate Linear Programming Approximation Accuracy ICML 2014 A New Perspective on Learning Linear Separators with Large L_qL_p Margins AISTATS 2014 An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning COLT 2014 A second-order bound with excess losses COLT 2014 A Statistical Convergence Perspective of Algorithms for Rank Aggregation from Pairwise Data ICML 2014 A Unified Framework for Consistency of Regularized Loss Minimizers ICML 2014 Best-Arm Identification in Linear Bandits NeurIPS 2014 Beyond Disagreement-Based Agnostic Active Learning NeurIPS 2014 Bias in Natural Actor-Critic Algorithms ICML 2014 Bounded Regret for Finite-Armed Structured Bandits NeurIPS 2014 Combinatorial Pure Exploration of Multi-Armed Bandits NeurIPS 2014