Frank-Wolfe Style Algorithms for Large Scale Optimization
Ding, Lijun, Madeleine Udell · arXiv (Cornell University) · 2018
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 $\mathcal{O}(\frac{1}{k})$.