Frank-Wolfe Style Algorithms for Large Scale Optimization
Optimization and Control
2018-08-17 v1 Machine Learning
Abstract
We introduce a few variants on Frank-Wolfe style algorithms suitable for large scale optimization. We show how to modify the standard Frank-Wolfe algorithm using stochastic gradients, approximate subproblem solutions, and sketched decision variables in order to scale to enormous problems while preserving (up to constants) the optimal convergence rate .
Cite
@article{arxiv.1808.05274,
title = {Frank-Wolfe Style Algorithms for Large Scale Optimization},
author = {Lijun Ding and Madeleine Udell},
journal= {arXiv preprint arXiv:1808.05274},
year = {2018}
}
Comments
28 pages, 5 figures, a chapter of the book "Large-Scale and Distributed Optimization", Springer's Lecture Notes in Mathematics Series, volume 2227, https://www.springer.com/us/book/9783319974774