Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jia, Kai, Rinard, Martin
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2311.06205
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910310319783936
author Jia, Kai
Rinard, Martin
author_facet Jia, Kai
Rinard, Martin
contents We present the Trust Region Adversarial Functional Subdifferential (TRAFS) algorithm for constrained optimization of nonsmooth convex Lipschitz functions. Unlike previous methods that assume a subgradient oracle model, we work with the functional subdifferential defined as a set of subgradients that simultaneously captures sufficient local information for effective minimization while being easy to compute for a wide range of functions. In each iteration, TRAFS finds the best step vector in an $\ell_2$-bounded trust region by considering the worst bound given by the functional subdifferential. TRAFS finds an approximate solution with an absolute error up to $ε$ in $\mathcal{O}\left( ε^{-1}\right)$ or $\mathcal{O}\left(ε^{-0.5} \right)$ iterations depending on whether the objective function is strongly convex, compared to the previously best-known bounds of $\mathcal{O}\left(ε^{-2}\right)$ and $\mathcal{O}\left(ε^{-1}\right)$ in these settings. TRAFS makes faster progress if the functional subdifferential satisfies a locally quadratic property; as a corollary, TRAFS achieves linear convergence (i.e., $\mathcal{O}\left(\log ε^{-1}\right)$) for strongly convex smooth functions. In the numerical experiments, TRAFS is on average 39.1x faster and solves twice as many problems compared to the second-best method.
format Preprint
id arxiv_https___arxiv_org_abs_2311_06205
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity
Jia, Kai
Rinard, Martin
Optimization and Control
Numerical Analysis
We present the Trust Region Adversarial Functional Subdifferential (TRAFS) algorithm for constrained optimization of nonsmooth convex Lipschitz functions. Unlike previous methods that assume a subgradient oracle model, we work with the functional subdifferential defined as a set of subgradients that simultaneously captures sufficient local information for effective minimization while being easy to compute for a wide range of functions. In each iteration, TRAFS finds the best step vector in an $\ell_2$-bounded trust region by considering the worst bound given by the functional subdifferential. TRAFS finds an approximate solution with an absolute error up to $ε$ in $\mathcal{O}\left( ε^{-1}\right)$ or $\mathcal{O}\left(ε^{-0.5} \right)$ iterations depending on whether the objective function is strongly convex, compared to the previously best-known bounds of $\mathcal{O}\left(ε^{-2}\right)$ and $\mathcal{O}\left(ε^{-1}\right)$ in these settings. TRAFS makes faster progress if the functional subdifferential satisfies a locally quadratic property; as a corollary, TRAFS achieves linear convergence (i.e., $\mathcal{O}\left(\log ε^{-1}\right)$) for strongly convex smooth functions. In the numerical experiments, TRAFS is on average 39.1x faster and solves twice as many problems compared to the second-best method.
title TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity
topic Optimization and Control
Numerical Analysis
url https://arxiv.org/abs/2311.06205