Skip to Main content Skip to Navigation
Conference papers

Nonstochastic Bandits with Composite Anonymous Feedback

Nicolo Cesa-Bianchi 1 Claudio Gentile 2, 3 Yishay Mansour 4, 3
2 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : We investigate a nonstochastic bandit setting in which the loss of an action is not immediately charged to the player, but rather spread over at most d consecutive steps in an adversarial way. This implies that the instantaneous loss observed by the player at the end of each round is a sum of as many as d loss components of previously played actions. Hence, unlike the standard bandit setting with delayed feedback, here the player cannot observe the individual delayed losses, but only their sum. Our main contribution is a general reduction transforming a standard bandit algorithm into one that can operate in this harder setting. We also show how the regret of the transformed algorithm can be bounded in terms of the regret of the original algorithm. Our reduction cannot be improved in general: we prove a lower bound on the regret of any bandit algorithm in this setting that matches (up to log factors) the upper bound obtained via our reduction. Finally, we show how our reduction can be extended to more complex bandit settings, such as combinatorial linear bandits and online bandit convex optimization.
Document type :
Conference papers
Complete list of metadata

Cited literature [16 references]  Display  Hide  Download
Contributor : Claudio Gentile Connect in order to contact the contributor
Submitted on : Friday, November 9, 2018 - 3:48:52 AM
Last modification on : Friday, January 21, 2022 - 3:11:09 AM
Long-term archiving on: : Sunday, February 10, 2019 - 12:21:10 PM


Files produced by the author(s)


  • HAL Id : hal-01916981, version 1


Nicolo Cesa-Bianchi, Claudio Gentile, Yishay Mansour. Nonstochastic Bandits with Composite Anonymous Feedback. COLT 2018 - 31st Annual Conference on Learning Theory, Jul 2018, Stockholm, Sweden. pp.1 - 23. ⟨hal-01916981⟩



Les métriques sont temporairement indisponibles