A Simple Method for Convex Optimization in the Oracle Model
Abstract
We give a simple and natural method for computing approximately optimal solutions for minimizing a convex function over a convex set given by a separation oracle. Our method utilizes the Frank--Wolfe algorithm over the cone of valid inequalities of and subgradients of . Under the assumption that is -Lipschitz and that contains a ball of radius and is contained inside the origin centered ball of radius , using iterations and calls to the oracle, our main method outputs a point satisfying . Our algorithm is easy to implement, and we believe it can serve as a useful alternative to existing cutting plane methods. As evidence towards this, we show that it compares favorably in terms of iteration counts to the standard LP based cutting plane method and the analytic center cutting plane method, on a testbed of combinatorial, semidefinite and machine learning instances.
Cite
@article{arxiv.2011.08557,
title = {A Simple Method for Convex Optimization in the Oracle Model},
author = {Daniel Dadush and Christopher Hojny and Sophie Huiberts and Stefan Weltge},
journal= {arXiv preprint arXiv:2011.08557},
year = {2022}
}
Comments
minor changes; to appear at IPCO 2022