An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
Machine Learning
2015-08-03 v1 Optimization and Control
Machine Learning
Abstract
We consider the closely related problems of bandit convex optimization with two-point feedback, and zero-order stochastic convex optimization with two function evaluations per round. We provide a simple algorithm and analysis which is optimal for convex Lipschitz functions. This improves on \cite{dujww13}, which only provides an optimal result for smooth functions; Moreover, the algorithm and analysis are simpler, and readily extend to non-Euclidean problems. The algorithm is based on a small but surprisingly powerful modification of the gradient estimator.
Cite
@article{arxiv.1507.08752,
title = {An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback},
author = {Ohad Shamir},
journal= {arXiv preprint arXiv:1507.08752},
year = {2015}
}
Comments
9 pages