[IDA ML Seminar] Machine Learning Seminar, 6/12 at 15:15: Devdatt Dubhashi, Chalmers, "Pure Exploration in Bandits with Linear Constraints"

[Fredrik Lindsten]

Welcome to an IDA Machine Learning Seminar on Wednesday, December 6 at 15:15 in Ada Lovelace

Pure Exploration in Bandits with Linear Constraints
Devdatt Dubhashi<https://research.chalmers.se/person/dubhashi>, Professor, Chalmers University of Technology

Abstract: We address the problem of identifying the optimal policy with fixed confidence in a multi-armed bandit setup, when the arms are subject to linear constraints. Unlike the standard best-arm identification problem which is well studied, the optimal policy in this case may not be deterministic and could mix between several arms. This changes the geometry of the problem which we characterize via an information-theoretic lower bound. We introduce two asymptotically optimal algorithms for this setting, one based on the Track-and-Stop method and the other based on a game-theoretic approach. Both these algorithms try to track an optimal allocation based on the lower bound and computed by a weighted projection onto the boundary of a normal cone. Finally, we provide empirical results that validate our bounds and visualize how constraints change the hardness of the problem.

Location: Ada Lovelace, https://www.ida.liu.se/department/location/search.en.shtml?keyword=ada

------------------

The list of future seminars in the series is available at: http://www.ida.liu.se/research/machinelearning/seminars/
You can subscribe to the seminar series' calendar using this ics link: https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.liu.se/pipermail/ml-seminars/attachments/20231128/1a59ea7b/attachment.htm>