TY - GEN
T1 - Better Best of Both Worlds Bounds for Bandits with Switching Costs
AU - Amir, Idan
AU - Azov, Guy
AU - Koren, Tomer
AU - Livni, Roi
N1 - Publisher Copyright:
© 2022 Neural information processing systems foundation. All rights reserved.
PY - 2022
Y1 - 2022
N2 - We study best-of-both-worlds algorithms for bandits with switching cost, recently addressed by Rouyer, Seldin, and Cesa-Bianchi [14]. We introduce a surprisingly simple and effective algorithm that simultaneously achieves minimax optimal regret bound (up to logarithmic factors) of O(T2/3) in the oblivious adversarial setting and a bound of O(min{log(T)/∆2,T2/3}) in the stochastically-constrained regime, both with (unit) switching costs, where ∆ is the gap between the arms. In the stochastically constrained case, our bound improves over previous results due to [14], that achieved regret of O(T1/3/∆). We accompany our results with a lower bound showing that, in general, Ω̃(min{1/∆2,T2/3}) switching cost regret is unavoidable in the stochastically-constrained case for algorithms with O(T2/3) worst-case switching cost regret.
AB - We study best-of-both-worlds algorithms for bandits with switching cost, recently addressed by Rouyer, Seldin, and Cesa-Bianchi [14]. We introduce a surprisingly simple and effective algorithm that simultaneously achieves minimax optimal regret bound (up to logarithmic factors) of O(T2/3) in the oblivious adversarial setting and a bound of O(min{log(T)/∆2,T2/3}) in the stochastically-constrained regime, both with (unit) switching costs, where ∆ is the gap between the arms. In the stochastically constrained case, our bound improves over previous results due to [14], that achieved regret of O(T1/3/∆). We accompany our results with a lower bound showing that, in general, Ω̃(min{1/∆2,T2/3}) switching cost regret is unavoidable in the stochastically-constrained case for algorithms with O(T2/3) worst-case switching cost regret.
UR - http://www.scopus.com/inward/record.url?scp=85146210267&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85146210267
T3 - Advances in Neural Information Processing Systems
BT - Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
A2 - Koyejo, S.
A2 - Mohamed, S.
A2 - Agarwal, A.
A2 - Belgrave, D.
A2 - Cho, K.
A2 - Oh, A.
PB - Neural information processing systems foundation
T2 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
Y2 - 28 November 2022 through 9 December 2022
ER -