By A Mystery Man Writer
Regret Bounds for Batched Bandits
Yuichi Yoshida · SlidesLive
On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems
Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent
Condorcet Relaxation In Spatial Voting
Multinomial Logit Contextual Bandits: Provable Optimality and Practicality
Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent
Improving Causal Discovery By Optimal Bayesian Network Learning
Multinomial Logit Contextual Bandits: Provable Optimality and Practicality
Shinji Ito, Shuichi Hirahara, Tasuku Soma, Yuichi Yoshida · Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits · SlidesLive
Yuichi Yoshida · SlidesLive
Condorcet Relaxation In Spatial Voting
On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems
On Online Optimization: Dynamic Regret Analysis of Strongly Convex and Smooth Problems
Improving Causal Discovery By Optimal Bayesian Network Learning