Online Learning

Tight Bounds on Profile Redundancy and Distinguishability NeurIPS 2012 Truly Nonparametric Online Variational Inference for Hierarchical Dirichlet Processes NeurIPS 2012 Truncation-free Online Variational Inference for Bayesian Nonparametric Models NeurIPS 2012 Unified Algorithms for Online Learning and Competitive Analysis COLT 2012 Adaptive Hedge NeurIPS 2011 A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences COLT 2011 Agnostic KWIK learning and efficient approximate reinforcement learning COLT 2011 A simple multi-armed bandit algorithm with optimal variation-bounded regret COLT 2011 Bandits, Query Learning, and the Haystack Dimension COLT 2011 Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization COLT 2011 Blackwell Approachability and No-Regret Learning are Equivalent COLT 2011 Bounds on Individual Risk for Log-loss Predictors COLT 2011 Budgeted Optimization with Concurrent Stochastic-Duration Experiments NeurIPS 2011 Committing Bandits NeurIPS 2011 Confidence Weighted Mean Reversion Strategy for On-Line Portfolio Selection AISTATS 2011 Contextual Bandit Algorithms with Supervised Learning Guarantees AISTATS 2011 Does an Efficient Calibrated Forecasting Strategy Exist? COLT 2011 Efficient Online Learning via Randomized Rounding NeurIPS 2011 From Bandits to Experts: On the Value of Side-Observations NeurIPS 2011 Iterative Learning for Reliable Crowdsourcing Systems NeurIPS 2011 Learning Eigenvectors for Free NeurIPS 2011 Minimax Policies for Combinatorial Prediction Games COLT 2011 Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments COLT 2011 Missing Information Impediments to Learnability COLT 2011 Multi-armed bandits on implicit metric spaces NeurIPS 2011