Papers
Topics
Authors
Recent
Search
2000 character limit reached

Adversarial Dueling Bandits

Published 27 Oct 2020 in cs.LG and stat.ML | (2010.14563v1)

Abstract: 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 TT-round regret compared to the \emph{Borda-winner} from a set of KK items is O~(K1/3T2/3)\tilde{O}(K^{1/3}T^{2/3}), as well as a matching Ω(K1/3T2/3)\Omega(K^{1/3}T^{2/3}) lower bound. We also prove a similar high probability regret bound. We further consider a simpler \emph{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 O~((K/Δ2)log⁡T)\smash{ \tilde{O}((K/\Delta^2)\log{T}) } regret algorithm, where Δ\Delta is the gap in Borda scores between the best item and all other items, and show a lower bound of Ω(K/Δ2)\Omega(K/\Delta^2) indicating that our dependence on the main problem parameters KK and Δ\Delta is tight (up to logarithmic factors).

Citations (21)

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.