Salvato in:
Dettagli Bibliografici
Autori principali: An, Qi, Wang, Jiao, Niu, Zequn, Zhang, Nana
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.19541
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917879964762112
author An, Qi
Wang, Jiao
Niu, Zequn
Zhang, Nana
author_facet An, Qi
Wang, Jiao
Niu, Zequn
Zhang, Nana
contents In this study, we focus on computing the projection onto the $\ell_p$ quasi-norm ball, which is challenging due to the non-convex and non-Lipschitz nature inherent in the $\ell_p$ quasi-norm with $0<p<1$. We propose a novel localized approximation method that yields a Lipschitz continuous concave surrogate function for the $\ell_p$ quasi-norm with improved approximation quality. Building on this approximation, we enhance the state-of-the-art iterative reweighted algorithm proposed by Yang et al. (J Mach Learn Res 23:1-31, 2022) by constructing tighter subproblems. This improved algorithm solves the $\ell_p$ quasinorm ball projection problem through a series of tractable projections onto the weighted $\ell_1$ norm balls. Convergence analyses and numerical studies demonstrate the global convergence and superior computational efficiency of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19541
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Computation of the Non-convex Quasi-norm Ball Projection with Iterative Reweighted Approach
An, Qi
Wang, Jiao
Niu, Zequn
Zhang, Nana
Optimization and Control
In this study, we focus on computing the projection onto the $\ell_p$ quasi-norm ball, which is challenging due to the non-convex and non-Lipschitz nature inherent in the $\ell_p$ quasi-norm with $0<p<1$. We propose a novel localized approximation method that yields a Lipschitz continuous concave surrogate function for the $\ell_p$ quasi-norm with improved approximation quality. Building on this approximation, we enhance the state-of-the-art iterative reweighted algorithm proposed by Yang et al. (J Mach Learn Res 23:1-31, 2022) by constructing tighter subproblems. This improved algorithm solves the $\ell_p$ quasinorm ball projection problem through a series of tractable projections onto the weighted $\ell_1$ norm balls. Convergence analyses and numerical studies demonstrate the global convergence and superior computational efficiency of the proposed method.
title Efficient Computation of the Non-convex Quasi-norm Ball Projection with Iterative Reweighted Approach
topic Optimization and Control
url https://arxiv.org/abs/2412.19541