An Optimal Algorithm for Linear Bandits

Computer Science – Learning

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

This paper is superseded by S. Bubeck, N. Cesa-Bianchi, and S.M. Kakade, "Towards minimax policies for online linear optimizat

Scientific paper

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from convex geometry to construct what is essentially an optimal exploration basis. We also present an application to a model of linear bandits with expert advice. Interestingly, these results show that bandit linear optimization with expert advice in d dimensions is no more difficult (in terms of the achievable regret) than the online d-armed bandit problem with expert advice (where EXP4 is optimal).

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

An Optimal Algorithm for Linear Bandits does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with An Optimal Algorithm for Linear Bandits, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and An Optimal Algorithm for Linear Bandits will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-597559

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.