Abstract: Best-Of-Both-Worlds (BOBW) bandit algorithms that have regret guarantees for both stochastic and adversarial settings have been studied for many years and Tsallis-INF (or other FTRL policies) is one of the most promising frameworks f...

Joint Conference on Statistics and Data Science in China (JCSDS) is an international academic conference, jointly sponsored by the Chinese Association for Applied Statistics, the Statistics and Probability Association, Chinese Association for Industr...

Abstract: Recently, multi-armed bandit algorithms have been deployed in many realistic large-scale applications, i.e., ranking of search engines and acceleration of model selection. In these cases, the workload represented by the number o...