Online Algorithms

Fighting Bandits with a New Kind of Smoothness NeurIPS 2015 First-order regret bounds for combinatorial semi-bandits COLT 2015 Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints COLT 2015 Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning ICML 2015 Linear Multi-Resource Allocation with Semi-Bandit Feedback NeurIPS 2015 Minimax Fixed-Design Linear Regression COLT 2015 On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments ICML 2015 Online Density Estimation of Bradley-Terry Models COLT 2015 Online Gradient Boosting NeurIPS 2015 On-Line Learning Algorithms for Path Experts with Non-Additive Losses COLT 2015 Online Learning of Eigenvectors ICML 2015 Online Learning via Sequential Complexities JMLR 2015 Online Learning with Adversarial Delays NeurIPS 2015 Online Learning with Feedback Graphs: Beyond Bandits COLT 2015 Online Learning with Gaussian Payoffs and Side Observations NeurIPS 2015 Online Optimization : Competing with Dynamic Comparators AISTATS 2015 Online Sketching Hashing CVPR 2015 Online Time Series Prediction with Missing Data ICML 2015 On the Complexity of Bandit Linear Optimization COLT 2015 On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs NeurIPS 2015 Open Problem: Online Sabotaged Shortest Path COLT 2015 Plug-and-Play Dual-Tree Algorithm Runtime Analysis JMLR 2015 Predtron: A Family of Online Algorithms for General Prediction Problems NeurIPS 2015 Regret-Based Pruning in Extensive-Form Games NeurIPS 2015 Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem COLT 2015