Global non-asymptotic super-linear convergence rates of regularized proximal quasi-Newton methods on non-smooth composite problems
Abstract
In this paper, we propose two regularized proximal quasi-Newton methods with symmetric rank-1 update of the metric (SR1 quasi-Newton) to solve non-smooth convex additive composite problems. Both algorithms avoid using line search or other trust region strategies. For each of them, we prove a super-linear convergence rate that is independent of the initialization of the algorithm. The cubic regularized method achieves a rate of order , where is the number of iterations and is some constant, and the other gradient regularized method shows a rate of the order . To the best of our knowledge, these are the first global non-asymptotic super-linear convergence rates for regularized quasi-Newton methods and regularized proximal quasi-Newton methods. The theoretical properties are also demonstrated in two applications from machine learning.
Keywords
Cite
@article{arxiv.2410.11676,
title = {Global non-asymptotic super-linear convergence rates of regularized proximal quasi-Newton methods on non-smooth composite problems},
author = {Shida Wang and Jalal Fadili and Peter Ochs},
journal= {arXiv preprint arXiv:2410.11676},
year = {2024}
}