# Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms

arXiv: https://arxiv.org/abs/1409.6086 · HTML: https://mlsanity.com/paper/1409.6086/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2014.

## Built on by (most cited first, 3 of 3)

- [Distributed stochastic optimization with large delays](https://mlsanity.com/paper/2107.02919/) (2021)
- [Scalable Projection-Free Optimization](https://mlsanity.com/paper/2105.03527/) (2021)
- [Federated Frank-Wolfe Algorithm](https://mlsanity.com/paper/2408.10090/) (2024)

## Abstract (arXiv)

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 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~citeplacoste2013block. 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.