Lipschitz Bandits without the Lipschitz Constant

Details Lipschitz Bandits without the Lipschitz Constant Lipschitz Bandits without the Lipschitz Constant

2011-05-25

arxiv.org/abs/1105.5041v2

22nd International Conference on Algorithmic Learning Theory --- (ALT 2011), Espoo : Finland (2011)

Mathematics

Statistics Theory

Scientific paper

We consider the setting of stochastic bandit problems with a continuum of arms. We first point out that the strategies considered so far in the literature only provided theoretical guarantees of the form: given some tuning parameters, the regret is small with respect to a class of environments that depends on these parameters. This is however not the right perspective, as it is the strategy that should adapt to the specific bandit environment at hand, and not the other way round. Put differently, an adaptation issue is raised. We solve it for the special case of environments whose mean-payoff functions are globally Lipschitz. More precisely, we show that the minimax optimal orders of magnitude $L^{d/(d+2)} \, T^{(d+1)/(d+2)}$ of the regret bound against an environment $f$ with Lipschitz constant $L$ over $T$ time instances can be achieved without knowing $L$ or $T$ in advance. This is in contrast to all previously known strategies, which require to some extent the knowledge of $L$ to achieve this performance guarantee.

Affiliated with

Also associated with

No associations

Rating

Lipschitz Bandits without the Lipschitz Constant 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 Lipschitz Bandits without the Lipschitz Constant, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Lipschitz Bandits without the Lipschitz Constant will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-191665