Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms
Abstract
We develop parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework. Whenever possible, we perform computations asynchronously, which helps attain speedups on multicore machines as well as in distributed environments. Moreover, instead of worst-case bounded delays, our methods only depend (mildly) on \emph{expected} delays, allowing them to be robust to stragglers and faulty worker threads. Our algorithms assume block-separable constraints, and subsume the recent Block-Coordinate Frank-Wolfe (BCFW) method~\citep{lacoste2013block}. Our analysis reveals problem-dependent quantities that govern the speedups of our methods over BCFW. We present experiments on structural SVM and Group Fused Lasso, obtaining significant speedups over competing state-of-the-art (and synchronous) methods.
Cite
@article{arxiv.1409.6086,
title = {Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms},
author = {Yu-Xiang Wang and Veeranjaneyulu Sadhanala and Wei Dai and Willie Neiswanger and Suvrit Sra and Eric P. Xing},
journal= {arXiv preprint arXiv:1409.6086},
year = {2016}
}