learning theory

Near-optimal Regret Bounds for Reinforcement Learning JMLR 2010 On Finding Predictors for Arbitrary Families of Processes JMLR 2010 On the Theory of Learnining with Privileged Information NeurIPS 2010 Sample Complexity of Testing the Manifold Hypothesis NeurIPS 2010 Stability Bounds for Stationary φ-mixing and β-mixing Processes JMLR 2010 Tight Sample Complexity of Large-Margin Learning NeurIPS 2010 Asymptotically Optimal Regularization in Smooth Parametric Models NeurIPS 2009 Consistency and Localizability JMLR 2009 Discrete MDL Predicts in Total Variation NeurIPS 2009 Fast Learning from Non-i.i.d. Observations NeurIPS 2009 Human Rademacher Complexity NeurIPS 2009 On The Power of Membership Queries in Agnostic Learning JMLR 2009 A Moment Bound for Multi-hinge Classifiers JMLR 2008 From Online to Batch Learning with Cutoff-Averaging NeurIPS 2008 Learning from Multiple Sources JMLR 2008 Multi-stage Convex Relaxation for Learning with Sparse Regularization NeurIPS 2008 Rademacher Complexity Bounds for Non-I.I.D. Processes NeurIPS 2008 Cluster Stability for Finite Samples NeurIPS 2007 Learnability of Gaussians with Flexible Variances JMLR 2007 Progressive mixture rules are deviation suboptimal NeurIPS 2007 Separating Models of Learning from Correlated and Uncorrelated Data JMLR 2007 Stability Bounds for Non-i.i.d. Processes NeurIPS 2007 The Tradeoffs of Large Scale Learning NeurIPS 2007 Unlabeled Compression Schemes for Maximum Classes JMLR 2007 VC Theory of Large Margin Multi-Category Classifiers JMLR 2007