Proximal random reshuffling under local Lipschitz continuity
Optimization and Control
2024-08-15 v1
Abstract
We study proximal random reshuffling for minimizing the sum of locally Lipschitz functions and a proper lower semicontinuous convex function without assuming coercivity or the existence of limit points. The algorithmic guarantees pertaining to near approximate stationarity rely on a new tracking lemma linking the iterates to trajectories of conservative fields. One of the novelties in the analysis consists in handling conservative fields with unbounded values.
Cite
@article{arxiv.2408.07182,
title = {Proximal random reshuffling under local Lipschitz continuity},
author = {Cedric Josz and Lexiao Lai and Xiaopeng Li},
journal= {arXiv preprint arXiv:2408.07182},
year = {2024}
}