Frank-Wolfe Style Algorithms for Large Scale Optimization

08/15/2018

∙

by   Lijun Ding, et al.

∙

0

∙

share

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 O(1/k).