Saved in:
Bibliographic Details
Main Author: Li, Jiongcheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.11286
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910702924464128
author Li, Jiongcheng
author_facet Li, Jiongcheng
contents Optimization problems, arise in many practical applications, from the view points of both theory and numerical methods. Especially, significant improvement in deep learning training came from the Quasi-Newton methods. Quasi-Newton search directions provide an attractive alternative to Newton's method in that they do not require computation of the Hessian and yet still attain a super linear rate of convergence. In Quasi-Newton method, we require Hessian approximation to satisfy the secant equation. In this paper, the Classical Cauchy-Schwartz Inequality is introduced, then more generalization are proposed. And it is seriously proved that Quasi-Newton method is a steepest descent method under the ellipsoid norm.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11286
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quasi-Newton method of Optimization is proved to be a steepest descent method under the ellipsoid norm
Li, Jiongcheng
Optimization and Control
Optimization problems, arise in many practical applications, from the view points of both theory and numerical methods. Especially, significant improvement in deep learning training came from the Quasi-Newton methods. Quasi-Newton search directions provide an attractive alternative to Newton's method in that they do not require computation of the Hessian and yet still attain a super linear rate of convergence. In Quasi-Newton method, we require Hessian approximation to satisfy the secant equation. In this paper, the Classical Cauchy-Schwartz Inequality is introduced, then more generalization are proposed. And it is seriously proved that Quasi-Newton method is a steepest descent method under the ellipsoid norm.
title Quasi-Newton method of Optimization is proved to be a steepest descent method under the ellipsoid norm
topic Optimization and Control
url https://arxiv.org/abs/2411.11286