Online Algorithms

Multi-Player Bandits – a Musical Chairs Approach ICML 2016 Multiple-Play Bandits in the Position-Based Model NeurIPS 2016 No-Regret Algorithms for Heavy-Tailed Linear Bandits ICML 2016 Online Collaborative Learning for Open-Vocabulary Visual Classifiers CVPR 2016 Online Convex Optimization with Unconstrained Domains and Losses NeurIPS 2016 Online Learning and Blackwell Approachability in Quitting Games COLT 2016 Online Learning with Feedback Graphs Without the Graphs ICML 2016 Online Learning with Low Rank Experts COLT 2016 Online Learning with Noisy Side Observations AISTATS 2016 Online Pricing with Strategic and Patient Buyers NeurIPS 2016 Online Sparse Linear Regression COLT 2016 On the capacity of information processing systems COLT 2016 On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models JMLR 2016 Open Problem: Parameter-Free and Scale-Free Online Algorithms COLT 2016 Optimal Best Arm Identification with Fixed Confidence COLT 2016 Optimistic Gittins Indices NeurIPS 2016 Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent NeurIPS 2016 Refined Lower Bounds for Adversarial Bandits NeurIPS 2016 Regret of Queueing Bandits NeurIPS 2016 REX: A Development Platform and Online Learning Approach for Runtime Emergent Software Systems OSDI 2016 Simple Bayesian Algorithms for Best Arm Identification COLT 2016 The Forget-me-not Process NeurIPS 2016 The Multi-fidelity Multi-armed Bandit NeurIPS 2016 Threshold Bandits, With and Without Censored Feedback NeurIPS 2016 Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient ICML 2016