Learning Theory

The lasso, persistence, and cross-validation ICML 2013 The Pareto Regret Frontier NeurIPS 2013 The Rate of Convergence of AdaBoost JMLR 2013 The Sample-Complexity of General Reinforcement Learning ICML 2013 Tracking Time-varying Graphical Structure NeurIPS 2013 Two-Sided Exponential Concentration Bounds for Bayes Error Rate and Shannon Entropy ICML 2013 Universal Consistency of Localized Versions of Regularized Kernel Methods JMLR 2013 Active Learning of Multi-Index Function Models NeurIPS 2012 Activized Learning: Transforming Passive to Active with Improved Label Complexity JMLR 2012 A Geometric Approach to Sample Compression JMLR 2012 A Linear Time Active Learning Algorithm for Link Classification NeurIPS 2012 A Primal-Dual Convergence Analysis of Boosting JMLR 2012 Attribute-Efficient Learning andWeight-Degree Tradeoffs for Polynomial Threshold Functions COLT 2012 Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence NeurIPS 2012 Beyond Logarithmic Bounds in Online Learning AISTATS 2012 Classification Calibration Dimension for General Multiclass Losses NeurIPS 2012 Computational Bounds on Statistical Query Learning COLT 2012 Confusion-Based Online Learning and a Passive-Aggressive Scheme NeurIPS 2012 Convergence Rate Analysis of MAP Coordinate Minimization Algorithms NeurIPS 2012 Density Propagation and Improved Bounds on the Partition Function NeurIPS 2012 Deterministic Annealing for Semi-Supervised Structured Output Learning AISTATS 2012 Dimensionality Dependent PAC-Bayes Margin Bound NeurIPS 2012 Distributed Learning, Communication Complexity and Privacy COLT 2012 Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space AISTATS 2012 Exploration in Model-based Reinforcement Learning by Empirically Estimating Learning Progress NeurIPS 2012