Beyond First-Order Methods for $\ell_p$-Structured Non-Monotone Variational Inequalities

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vyas, Abhijeet, Bullins, Brian
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914392566661120
author Vyas, Abhijeet
Bullins, Brian
author_facet Vyas, Abhijeet
Bullins, Brian
contents We propose novel high-order algorithms for a class of $\ell_p$-structured non-monotone variational inequalities. In particular, work by Diakonikolas et al. (2021), which introduced the weak Minty variational inequality (weak-MVI) setting, showed how to find an approximate first-order Euclidean stationary point for a strictly positive range of the weak-MVI parameter $ρ$. However, for the $\ell_p$-norm stationary point setting ($p \neq 2$), their guarantees are limited to $ρ=0$, which recovers the standard MVI setting. In this work, we address this gap by presenting a suite of high-order methods that converge to $\ell_p$-norm stationary points for a suitable range of $ρ> 0$, thereby circumventing previous fundamental challenges in $\ell_p$ settings. We further show convergence for high-order smooth \textit{monotone} operators, generalizing Adil et al. (2022) to the case where $p \geq 2$, and we extend our Euclidean techniques to continuous-time settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13491
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond First-Order Methods for $\ell_p$-Structured Non-Monotone Variational Inequalities
Vyas, Abhijeet
Bullins, Brian
Optimization and Control
We propose novel high-order algorithms for a class of $\ell_p$-structured non-monotone variational inequalities. In particular, work by Diakonikolas et al. (2021), which introduced the weak Minty variational inequality (weak-MVI) setting, showed how to find an approximate first-order Euclidean stationary point for a strictly positive range of the weak-MVI parameter $ρ$. However, for the $\ell_p$-norm stationary point setting ($p \neq 2$), their guarantees are limited to $ρ=0$, which recovers the standard MVI setting. In this work, we address this gap by presenting a suite of high-order methods that converge to $\ell_p$-norm stationary points for a suitable range of $ρ> 0$, thereby circumventing previous fundamental challenges in $\ell_p$ settings. We further show convergence for high-order smooth \textit{monotone} operators, generalizing Adil et al. (2022) to the case where $p \geq 2$, and we extend our Euclidean techniques to continuous-time settings.
title Beyond First-Order Methods for $\ell_p$-Structured Non-Monotone Variational Inequalities
topic Optimization and Control
url https://arxiv.org/abs/2603.13491