Non-convex Conditional Gradient Sliding
Optimization and Control
2017-08-17 v1
Abstract
We investigate a projection free method, namely conditional gradient sliding on batched, stochastic and finite-sum non-convex problem. CGS is a smart combination of Nesterov's accelerated gradient method and Frank-Wolfe (FW) method, and outperforms FW in the convex setting by saving gradient computations. However, the study of CGS in the non-convex setting is limited. In this paper, we propose the non-convex conditional gradient sliding (NCGS) which surpasses the non-convex Frank-Wolfe method in batched, stochastic and finite-sum setting.
Cite
@article{arxiv.1708.04783,
title = {Non-convex Conditional Gradient Sliding},
author = {Chao Qu and Yan Li and Huan Xu},
journal= {arXiv preprint arXiv:1708.04783},
year = {2017}
}