Adversarial Dueling Bandits

Aadirupa Saha*, Tomer Koren, Yishay Mansour

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We introduce the problem of regret minimization in Adversarial Dueling Bandits. As in classic Dueling Bandits, the learner has to repeatedly choose a pair of items and observe only a relative binary 'win-loss' feedback for this pair, but here this feedback is generated from an arbitrary preference matrix, possibly chosen adversarially. Our main result is an algorithm whose T-round regret compared to the Borda-winner from a set of K items is Õ(K1/3T2/3), as well as a matching Ω(K1/3T2/3) lower bound. We also prove a similar high probability regret bound. We further consider a simpler fixed-gap adversarial setup, which bridges between two extreme preference feedback models for dueling bandits: stationary preferences and an arbitrary sequence of preferences. For the fixed-gap adversarial setup we give an Õ((K/∆2) log T) regret algorithm, where ∆ is the gap in Borda scores between the best item and all other items, and show a lower bound of Ω(K/∆2) indicating that our dependence on the main problem parameters K and ∆ is tight (up to logarithmic factors). Finally, we corroborate the theoretical results with empirical evaluations.

Original languageEnglish
Title of host publicationProceedings of the 38th International Conference on Machine Learning, ICML 2021
PublisherML Research Press
Number of pages10
ISBN (Electronic)9781713845065
StatePublished - 2021
Event38th International Conference on Machine Learning, ICML 2021 - Virtual, Online
Duration: 18 Jul 202124 Jul 2021

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


Conference38th International Conference on Machine Learning, ICML 2021
CityVirtual, Online


Dive into the research topics of 'Adversarial Dueling Bandits'. Together they form a unique fingerprint.

Cite this