ICML 2025poster0 citations
Secant Line Search for Frank-Wolfe Algorithms
Deborah Hendrych, Sebastian Pokutta, Mathieu Besançon, David Martínez-Rubio
Abstract
We present a new step-size strategy based on the secant method for Frank-Wolfe algorithms. This strategy, which requires mild assumptions about the function under consideration, can be applied to any Frank-Wolfe algorithm. It is as effective as full line search and, in particular, allows for adapting to the local smoothness of the function, such as in (Pedregosa et al., 2020), but comes with a significantly reduced computational cost, leading to higher effective rates of convergence. We provide theoretical guarantees and demonstrate the effectiveness of the strategy through numerical experiments.
First-order methodsFrank-Wolfe algorithmsSecant
BibTeX
@inproceedings{
hendrych2025secant,
title={Secant Line Search for Frank-Wolfe Algorithms},
author={Deborah Hendrych and Sebastian Pokutta and Mathieu Besan{\c{c}}on and David Mart{\'\i}nez-Rubio},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=hgM387MPm1}
}