A fast quasi-Newton-type method for large-scale stochastic optimisation

Title: A fast quasi-Newton-type method for large-scale stochastic optimisation
Creator: Wills, Adrian; Schön, Thomas B.; Jidling, Carl
Relation: IFAC-PapersOnLine Vol. 53, Issue 2, p. 1249-1254
Publisher Link: http://dx.doi.org/10.1016/j.ifacol.2020.12.1849
Publisher: Elsevier
Resource Type: journal article
Date: 2020
Description: In recent years there has been an increased interest in stochastic adaptations of limited memory quasi-Newton methods, which compared to pure gradient-based routines can improve the convergence by incorporating second-order information. In this work we propose a direct least-squares approach conceptually similar to the limited memory quasi-Newton methods, but that computes the search direction in a slightly different way. This is achieved in a fast and numerically robust manner by maintaining a Cholesky factor of low dimension. The performance is demonstrated on real-world benchmark problems which shows improved results in comparison with already established methods.
Subject: optimisation problems; large-scale problems; stochastic systems; Cholesky factorisation; neural networks
Identifier: http://hdl.handle.net/1959.13/1442525
Identifier: uon:41712
Identifier: ISSN:2405-8963
Language: eng
Reviewed

		Thumbnail	File	Description	Size	Format