Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Godichon-Baggioni, Antoine, Lu, Wei, Portier, Bruno
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912265981132800
author Godichon-Baggioni, Antoine
Lu, Wei
Portier, Bruno
author_facet Godichon-Baggioni, Antoine
Lu, Wei
Portier, Bruno
contents This paper addresses second-order stochastic optimization for estimating the minimizer of a convex function written as an expectation. A direct recursive estimation technique for the inverse Hessian matrix using a Robbins-Monro procedure is introduced. This approach enables to drastically reduces computational complexity. Above all, it allows to develop universal stochastic Newton methods and investigate the asymptotic efficiency of the proposed approach. This work so expands the application scope of secondorder algorithms in stochastic optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10923
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms
Godichon-Baggioni, Antoine
Lu, Wei
Portier, Bruno
Optimization and Control
Machine Learning
This paper addresses second-order stochastic optimization for estimating the minimizer of a convex function written as an expectation. A direct recursive estimation technique for the inverse Hessian matrix using a Robbins-Monro procedure is introduced. This approach enables to drastically reduces computational complexity. Above all, it allows to develop universal stochastic Newton methods and investigate the asymptotic efficiency of the proposed approach. This work so expands the application scope of secondorder algorithms in stochastic optimization.
title Online estimation of the inverse of the Hessian for stochastic optimization with application to universal stochastic Newton algorithms
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2401.10923