2021-07-21-lattimore21b.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
Mirror Descent and the Information Ratio	We establish a connection between the stability of mirror descent and the information ratio by Russo and Van Roy (2014). Our analysis shows that mirror descent with suitable loss estimators and exploratory distributions enjoys the same bound on the adversarial regret as the bounds on the Bayesian regret for information-directed sampling. Along the way, we develop the theory for information-directed sampling and provide an efficient algorithm for adversarial bandits for which the regret upper bound matches exactly the best known information-theoretic upper bound. Keywords: Bandits, partial monitoring, mirror descent, information theory.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	lattimore21b	0	Mirror Descent and the Information Ratio	2965	2992	2965-2992	2965	false	Lattimore, Tor and Gyorgy, Andras	given family Tor Lattimore given family Andras Gyorgy	2021-07-21		Proceedings of Thirty Fourth Conference on Learning Theory	134	inproceedings	date-parts 2021 7 21	http://proceedings.mlr.press/v134/lattimore21b/lattimore21b.pdf