On Global Rates for Regularization Methods based on Secant Derivative Approximations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cartis, Coralia, Jerad, Sadok
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912578405400576
author Cartis, Coralia
Jerad, Sadok
author_facet Cartis, Coralia
Jerad, Sadok
contents An inexact framework for high-order adaptive regularization methods is presented, in which approximations may be used for the $p$th-order tensor, based on lower-order derivatives. Between each recalculation of the $p$th-order derivative approximation, a high-order secant equation can be used to update the $p$th-order tensor as proposed in (Welzel 2024) or the approximation can be kept constant in a lazy manner. When refreshing the $p$th-order tensor approximation after $m$ steps, an exact evaluation of the tensor or a finite difference approximation can be used with an explicit discretization stepsize. For all the newly adaptive regularization variants, we prove an $\mathcal{O}\left( \max[ ε_1^{-(p+1)/p}, \, ε_2^{(-p+1)/(p-1)} ] \right)$ bound on the number of iterations needed to reach an $(ε_1, \, ε_2)$ second-order stationary points. Discussions on the number of oracle calls for each introduced variant are also provided. When $p=2$, we obtain a second-order method that uses quasi-Newton approximations with an $\mathcal{O}\left(\max[ε_1^{-3/2}, \, \, ε_2^{-3}]\right)$ iteration bound to achieve approximate second-order stationarity.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07580
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Global Rates for Regularization Methods based on Secant Derivative Approximations
Cartis, Coralia
Jerad, Sadok
Optimization and Control
Numerical Analysis
An inexact framework for high-order adaptive regularization methods is presented, in which approximations may be used for the $p$th-order tensor, based on lower-order derivatives. Between each recalculation of the $p$th-order derivative approximation, a high-order secant equation can be used to update the $p$th-order tensor as proposed in (Welzel 2024) or the approximation can be kept constant in a lazy manner. When refreshing the $p$th-order tensor approximation after $m$ steps, an exact evaluation of the tensor or a finite difference approximation can be used with an explicit discretization stepsize. For all the newly adaptive regularization variants, we prove an $\mathcal{O}\left( \max[ ε_1^{-(p+1)/p}, \, ε_2^{(-p+1)/(p-1)} ] \right)$ bound on the number of iterations needed to reach an $(ε_1, \, ε_2)$ second-order stationary points. Discussions on the number of oracle calls for each introduced variant are also provided. When $p=2$, we obtain a second-order method that uses quasi-Newton approximations with an $\mathcal{O}\left(\max[ε_1^{-3/2}, \, \, ε_2^{-3}]\right)$ iteration bound to achieve approximate second-order stationarity.
title On Global Rates for Regularization Methods based on Secant Derivative Approximations
topic Optimization and Control
Numerical Analysis
url https://arxiv.org/abs/2509.07580