Online Algorithms

Threshold Bandits, With and Without Censored Feedback NeurIPS 2016 Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problem COLT 2016 Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient ICML 2016 Tracking the Best Expert in Non-stationary Stochastic Environments NeurIPS 2016 Achieving All with No Parameters: AdaNormalHedge COLT 2015 Adaptive Online Learning NeurIPS 2015 Adaptive Stochastic Optimization: From Sets to Paths NeurIPS 2015 Adaptive Strategy for Stratified Monte Carlo Sampling JMLR 2015 Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks NeurIPS 2015 A Square Root Inverse Filter for Efficient Vision-aided Inertial Navigation on Mobile Devices RSS 2015 Bandit Convex Optimization: \sqrtT Regret in One Dimension COLT 2015 Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff NeurIPS 2015 Batched Bandit Problems COLT 2015 Budgeted Bandit Problems with Continuous Random Costs ACML 2015 Cheap Bandits ICML 2015 Combinatorial Bandits Revisited NeurIPS 2015 Communication Complexity of Distributed Convex Learning and Optimization NeurIPS 2015 Competing with the Empirical Risk Minimizer in a Single Pass COLT 2015 Contextual Dueling Bandits COLT 2015 Copeland Dueling Bandits NeurIPS 2015 Efficient Learning in Large-Scale Combinatorial Semi-Bandits ICML 2015 Explore no more: Improved high-probability regret bounds for non-stochastic bandits NeurIPS 2015 Fast Convergence of Regularized Learning in Games NeurIPS 2015 Faster Algorithms for Testing under Conditional Sampling COLT 2015 Fast Rates in Statistical and Online Learning JMLR 2015