A Simple Linear Convergence Analysis of the Point-SAGA Algorithm
Optimization and Control
2024-05-31 v1
Abstract
Point-SAGA is a randomized algorithm for minimizing a sum of convex functions using their proximity operators (proxs), proposed by Defazio (2016). At every iteration, the prox of only one randomly chosen function is called. We generalize the algorithm to any number of prox calls per iteration, not only one, and propose a simple proof of linear convergence when the functions are smooth and strongly convex.
Keywords
Cite
@article{arxiv.2405.19951,
title = {A Simple Linear Convergence Analysis of the Point-SAGA Algorithm},
author = {Laurent Condat and Peter Richtárik},
journal= {arXiv preprint arXiv:2405.19951},
year = {2024}
}