On a multilevel Levenberg-Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations

In this paper, we propose a new multilevel Levenberg-Marquardt optimizer for the training of artificial neural networks with quadratic loss function. This setting allows us to get further insight into the potential of multilevel optimization methods. Indeed, when the least squares problem arises fro...

Full description

Saved in:
Bibliographic Details
Published inOptimization methods & software Vol. 37; no. 1; pp. 361 - 386
Main Authors Calandra, H., Gratton, S., Riccietti, E., Vasseur, X.
Format Journal Article
LanguageEnglish
Published Abingdon Taylor & Francis 02.01.2022
Taylor & Francis Ltd
Subjects
Online AccessGet full text
ISSN1055-6788
1029-4937
DOI10.1080/10556788.2020.1775828

Cover

More Information
Summary:In this paper, we propose a new multilevel Levenberg-Marquardt optimizer for the training of artificial neural networks with quadratic loss function. This setting allows us to get further insight into the potential of multilevel optimization methods. Indeed, when the least squares problem arises from the training of artificial neural networks, the variables subject to optimization are not related by any geometrical constraints and the standard interpolation and restriction operators cannot be employed any longer. A heuristic, inspired by algebraic multigrid methods, is then proposed to construct the multilevel transfer operators. We test the new optimizer on an important application: the approximate solution of partial differential equations by means of artificial neural networks. The learning problem is formulated as a least squares problem, choosing the nonlinear residual of the equation as a loss function, whereas the multilevel method is employed as a training method. Numerical experiments show encouraging results related to the efficiency of the new multilevel optimization method compared to the corresponding one-level procedure in this context.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1055-6788
1029-4937
DOI:10.1080/10556788.2020.1775828