Stochastic convex optimization with bandit feedback

Details Stochastic convex optimization with bandit feedback Stochastic convex optimization with bandit feedback

2011-07-08

arxiv.org/abs/1107.1744v2

Mathematics

Optimization and Control

Scientific paper

This paper addresses the problem of minimizing a convex, Lipschitz function $f$ over a convex, compact set $\xset$ under a stochastic bandit feedback model. In this model, the algorithm is allowed to observe noisy realizations of the function value $f(x)$ at any query point $x \in \xset$. The quantity of interest is the regret of the algorithm, which is the sum of the function values at algorithm's query points minus the optimal function value. We demonstrate a generalization of the ellipsoid algorithm that incurs $\otil(\poly(d)\sqrt{T})$ regret. Since any algorithm has regret at least $\Omega(\sqrt{T})$ on this problem, our algorithm is optimal in terms of the scaling with $T$.

Affiliated with

Also associated with

No associations

Rating

Stochastic convex optimization with bandit feedback 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 Stochastic convex optimization with bandit feedback, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Stochastic convex optimization with bandit feedback will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-674760