Salvato in:
Dettagli Bibliografici
Autori principali: Bodard, Alexander, Patrinos, Panagiotis
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.12666
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917488467378176
author Bodard, Alexander
Patrinos, Panagiotis
author_facet Bodard, Alexander
Patrinos, Panagiotis
contents Newton-type methods are typically analyzed under Lipschitz continuity of the Hessian, an assumption that can fail for objectives with higher-order or polynomial growth. We introduce a class of nonlinearly preconditioned Newton methods that apply Newton's root-finding scheme to a transformed optimality mapping, thereby extending recent nonlinear preconditioning ideas from first-order methods to the second-order setting. The resulting methods are naturally analyzed under Lipschitz continuity of a preconditioned Hessian, a condition that significantly relaxes the classical Hessian Lipschitz continuity assumption. Under this generalized smoothness model, we establish local superlinear and quadratic convergence guarantees, and develop a globalization strategy for the nonregularized method despite the fact that the preconditioned Newton direction need not be a descent direction. We further propose a regularized variant for isotropic preconditioners, and show that it attains an $O(\varepsilon^{-3/2})$ iteration complexity. An adaptive version removes the need to know the smoothness constant and allows inexact subproblem solutions while preserving the same complexity order.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12666
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach
Bodard, Alexander
Patrinos, Panagiotis
Optimization and Control
Newton-type methods are typically analyzed under Lipschitz continuity of the Hessian, an assumption that can fail for objectives with higher-order or polynomial growth. We introduce a class of nonlinearly preconditioned Newton methods that apply Newton's root-finding scheme to a transformed optimality mapping, thereby extending recent nonlinear preconditioning ideas from first-order methods to the second-order setting. The resulting methods are naturally analyzed under Lipschitz continuity of a preconditioned Hessian, a condition that significantly relaxes the classical Hessian Lipschitz continuity assumption. Under this generalized smoothness model, we establish local superlinear and quadratic convergence guarantees, and develop a globalization strategy for the nonregularized method despite the fact that the preconditioned Newton direction need not be a descent direction. We further propose a regularized variant for isotropic preconditioners, and show that it attains an $O(\varepsilon^{-3/2})$ iteration complexity. An adaptive version removes the need to know the smoothness constant and allows inexact subproblem solutions while preserving the same complexity order.
title Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach
topic Optimization and Control
url https://arxiv.org/abs/2605.12666