Learning Theory

Tracking the Best Expert in Non-stationary Stochastic Environments NeurIPS 2016 Train faster, generalize better: Stability of stochastic gradient descent ICML 2016 Why Most Decisions Are Easy in Tetris—And Perhaps in Other Sequential Decision Problems, As Well ICML 2016 Abstraction Selection in Model-based Reinforcement Learning ICML 2015 A Chaining Algorithm for Online Nonparametric Regression COLT 2015 Achievability of Asymptotic Minimax Regret by Horizon-Dependent and Horizon-Independent Strategies JMLR 2015 A Compression Technique for Analyzing Disagreement-Based Active Learning JMLR 2015 Adaptive Online Learning NeurIPS 2015 Agnostic Learning of Disjunctions on Symmetric Distributions JMLR 2015 Algorithmic Stability and Uniform Generalization NeurIPS 2015 An Almost Optimal PAC Algorithm COLT 2015 A New Look at Nearest Neighbours: Identifying Benign Input Geometries via Random Projections ACML 2015 A PTAS for Agnostically Learning Halfspaces COLT 2015 A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits ICML 2015 Bad Universal Priors and Notions of Optimality COLT 2015 Bandit Convex Optimization: \sqrtT Regret in One Dimension COLT 2015 Basis refinement strategies for linear value function approximation in MDPs NeurIPS 2015 Batched Bandit Problems COLT 2015 Competitive Distribution Estimation: Why is Good-Turing Good NeurIPS 2015 Complexity of Equivalence and Learning for Multiplicity Tree Automata JMLR 2015 Computational Complexity of Linear Large Margin Classification With Ramp Loss AISTATS 2015 Computational Lower Bounds for Community Detection on Random Graphs COLT 2015 Cornering Stationary and Restless Mixing Bandits with Remix-UCB NeurIPS 2015 Counterfactual Risk Minimization: Learning from Logged Bandit Feedback ICML 2015 Efficient and Parsimonious Agnostic Active Learning NeurIPS 2015