The Low-Memory Matrix Adaptation Evolution Strategy is a recent variant of CMA-ES that is specifically meant for large-scale numerical optimization. In this paper, we investigate if and how gradient information can be included in this algorithm, in order to enhance its performance. Furthermore, we consider the incorporation of Lévy flight to alleviate stability issues due to possibly unreliably gradient estimation as well as promote better exploration. In total, we propose four new variants of LMMA-ES, making use of real and estimated gradient, with and without Lévy flight. We test the proposed variants on two neural network training tasks, one for image classification through the newly introduced Forward-Forward paradigm, and one for a Reinforcement Learning problem, as well as five benchmark functions for numerical optimization.

Low-Memory Matrix Adaptation Evolution Strategies Exploiting Gradient Information and Lévy Flight / Lunelli, Riccardo; Iacca, Giovanni. - 14634:(2024), pp. 35-50. (Intervento presentato al convegno EvoApplications 2024 tenutosi a Aberystwyth nel 3rd -5th April 2024) [10.1007/978-3-031-56852-7_3].

Low-Memory Matrix Adaptation Evolution Strategies Exploiting Gradient Information and Lévy Flight

Iacca, Giovanni
2024-01-01

Abstract

The Low-Memory Matrix Adaptation Evolution Strategy is a recent variant of CMA-ES that is specifically meant for large-scale numerical optimization. In this paper, we investigate if and how gradient information can be included in this algorithm, in order to enhance its performance. Furthermore, we consider the incorporation of Lévy flight to alleviate stability issues due to possibly unreliably gradient estimation as well as promote better exploration. In total, we propose four new variants of LMMA-ES, making use of real and estimated gradient, with and without Lévy flight. We test the proposed variants on two neural network training tasks, one for image classification through the newly introduced Forward-Forward paradigm, and one for a Reinforcement Learning problem, as well as five benchmark functions for numerical optimization.
2024
Applications of Evolutionary Computation. EvoApplications 2024
Cham, Svizzera
Springer
9783031568510
9783031568527
Lunelli, Riccardo; Iacca, Giovanni
Low-Memory Matrix Adaptation Evolution Strategies Exploiting Gradient Information and Lévy Flight / Lunelli, Riccardo; Iacca, Giovanni. - 14634:(2024), pp. 35-50. (Intervento presentato al convegno EvoApplications 2024 tenutosi a Aberystwyth nel 3rd -5th April 2024) [10.1007/978-3-031-56852-7_3].
File in questo prodotto:
File Dimensione Formato  
Low-Memory Matrix Adaptation Evolution Strategies Exploiting Gradient Information and Lévy Flight.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.94 MB
Formato Adobe PDF
1.94 MB Adobe PDF   Visualizza/Apri
lunelli.pdf

embargo fino al 21/03/2025

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.72 MB
Formato Adobe PDF
1.72 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/405930
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact