Robert Schapire

regret bound (7) contextual bandit (6) online learning (5) adversarial learning (2) empirical risk minimization (2) game theory (2) policy learning (2) interactive learning (1) imitation learning (1) sample efficiency (1) supervised learning (1) alternating minimization (1) convex risk minimization (1) resource allocation (1) collaborative filtering (1) reward prediction (1) conditional probability (1) importance weighting (1) online convex optimization (1) matrix factorization (1)