Pure exploration and regret minimization in matching bandits

Sentenac, Flore, Yi, Jialin, Calauzènes, ‪Clément, Perchet, Vianney and Vojnovic, Milan ORCID: 0000-0003-1382-022X (2021) Pure exploration and regret minimization in matching bandits. In: Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research,139. Journal of Machine Learning Research, pp. 9434-9442.

Text (Pure Exploration and Regret Minimization in Matching Bandits) - Published Version Download (400kB)

• Author

Abstract

Finding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentially. We prove that it is possible to leverage a rank-1 assumption on the adjacency matrix to reduce the sample complexity and the regret of off-the-shelf algorithms up to reaching a linear dependency in the number of vertices (up to poly log terms).

Item Type:	Book Section
Official URL:	https://proceedings.mlr.press/v139/sentenac21a.htm...
Additional Information:	© 2022 The Author(s).
Divisions:	Statistics
Subjects:	H Social Sciences > HA Statistics
Date Deposited:	30 Sep 2022 09:39
Last Modified:	16 Nov 2024 23:18
URI:	http://eprints.lse.ac.uk/id/eprint/116713

Actions (login required)

View Item