Characterization of optimization problems that are solvable iteratively with linear convergence
Optimization and Control
2024-06-27 v3 Differential Geometry
Abstract
In this work, we state a general conjecture on the solvability of optimization problems via algorithms with linear convergence guarantees. We make a first step towards examining its correctness by fully characterizing the problems that are solvable via Riemannian gradient descent with linear convergence.
Cite
@article{arxiv.2402.12090,
title = {Characterization of optimization problems that are solvable iteratively with linear convergence},
author = {Foivos Alimisis},
journal= {arXiv preprint arXiv:2402.12090},
year = {2024}
}
Comments
MTNS2024 conference