Preselection Bandits

Bengs, Viktor und Hüllermeier, Eyke (Juli 2020): Preselection Bandits. 37th International Conference on Machine Learning, Virtual, July 12-18 2020. III, Hal Daumé und Singh, Aarti (Hrsg.): In: Proceedings of the 37th International Conference on Machine Learning, Bd. 119 PMLR. S. 778-787

Abstract

In this paper, we introduce the Preselection Bandit problem, in which the learner preselects a subset of arms (choice alternatives) for a user, which then chooses the final arm from this subset. The learner is not aware of the user’s preferences, but can learn them from observed choices. In our concrete setting, we allow these choices to be stochastic and model the user’s actions by means of the Plackett-Luce model. The learner’s main task is to preselect subsets that eventually lead to highly preferred choices. To formalize this goal, we introduce a reasonable notion of regret and derive lower bounds on the expected regret. Moreover, we propose algorithms for which the upper bound on expected regret matches the lower bound up to a logarithmic term of the time horizon.

• Dokumententyp: Konferenzbeitrag (Paper)
• Publikationsform: Publisher's Version
• Fakultät: Mathematik, Informatik und Statistik > Informatik > Künstliche Intelligenz und Maschinelles Lernen
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 000 Informatik, Wissen, Systeme