Bandits with Abstention under Expert Advice

arXiv:2402.14585v1 Announce Type: new
Abstract: We study the classic problem of prediction with expert advice under bandit feedback. Our model assumes that one action, corresponding to the learner's abstention from play, has no reward or loss on every trial. We propose the CBA algorithm, which exploits this assumption to obtain reward bounds that can significantly improve those of the classical Exp4 algorithm. We can view our problem as the aggregation of confidence-rated predictors when the learner has the option of …

abstract advice algorithm arxiv cba cs.lg every expert exploits feedback loss prediction stat.ml study type