2021-03-18-arora21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Corralling Stochastic Bandit Algorithms	We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm. We give two general algorithms for this setting, which we show benefit from favorable regret guarantees. We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward, and depends on the gap between the highest reward and other rewards.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	arora21a	0	Corralling Stochastic Bandit Algorithms	2116	2124	2116-2124	2116	false	Arora, Raman and Vanislavov Marinov, Teodor and Mohri, Mehryar	given family Raman Arora given family Teodor Vanislavov Marinov given family Mehryar Mohri	2021-03-18		Proceedings of The 24th International Conference on Artificial Intelligence and Statistics	130	inproceedings	date-parts 2021 3 18	http://proceedings.mlr.press/v130/arora21a/arora21a.pdf	label link Supplementary ZIP http://proceedings.mlr.press/v130/arora21a/arora21a-supp.zip