2022-06-28-anand22a.md

title	booktitle	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
Online Algorithms with Multiple Predictions	Proceedings of the 39th International Conference on Machine Learning	This paper studies online algorithms augmented with <em>multiple</em> machine-learned predictions. We give a generic algorithmic framework for online covering problems with multiple predictions that obtains an online solution that is competitive against the performance of the <em>best</em> solution obtained from the predictions. Our algorithm incorporates the use of predictions in the classic potential-based analysis of online algorithms. We apply our algorithmic framework to solve classical problems such as online set cover, (weighted) caching, and online facility location in the multiple predictions setting.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	anand22a	0	Online Algorithms with Multiple Predictions	582	598	582-598	582	false	Anand, Keerti and Ge, Rong and Kumar, Amit and Panigrahi, Debmalya	given family Keerti Anand given family Rong Ge given family Amit Kumar given family Debmalya Panigrahi	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/anand22a/anand22a.pdf