# Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls

arXiv: https://arxiv.org/abs/1910.07703 · HTML: https://mlsanity.com/paper/1910.07703/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2019.

## Built on by (most cited first, 1 of 1)

- [Scalable High-Dimensional Multivariate Linear Regression for Feature-Distributed Data](https://mlsanity.com/paper/2307.03410/) (2023)

## Abstract (arXiv)

Large-scale machine learning training suffers from two prior challenges, specifically for nuclear-norm constrained problems with distributed systems: the synchronization slowdown due to the straggling workers, and high communication costs. In this work, we propose an asynchronous Stochastic Frank Wolfe (SFW-asyn) method, which, for the first time, solves the two problems simultaneously, while successfully maintaining the same convergence rate as the vanilla SFW. We implement our algorithm in python (with MPI) to run on Amazon EC2, and demonstrate that SFW-asyn yields speed-ups almost linear to the number of machines compared to the vanilla SFW.