A Low-Rank Symplectic Gradient Adjustment Method for Computing Nash Equilibria

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vater, Nadja, Foglia, Katherine Rossella, Colao, Vittorio, Borzì, Alfio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911239628652544
author Vater, Nadja
Foglia, Katherine Rossella
Colao, Vittorio
Borzì, Alfio
author_facet Vater, Nadja
Foglia, Katherine Rossella
Colao, Vittorio
Borzì, Alfio
contents This work presents a theoretical and numerical investigation of the symplectic gradient adjustment (SGA) method and of a low-rank SGA (LRSGA) method for efficiently solving two-objective optimization problems in the framework of Nash games. The SGA method outperforms the gradient method by including second-order mixed derivatives computed at each iterate, which requires considerably larger computational effort. For this reason, a LRSGA method is proposed where the approximation to second-order mixed derivatives are obtained by rank-one updates. The theoretical analysis presented in this work focuses on novel convergence estimates for the SGA and LRSGA methods, including parameter bounds. The superior computational complexity of the LRSGA method is demonstrated in the training of a CLIP neural architecture, where the LRSGA method outperforms the SGA method by orders of magnitude smaller CPU time.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25716
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Low-Rank Symplectic Gradient Adjustment Method for Computing Nash Equilibria
Vater, Nadja
Foglia, Katherine Rossella
Colao, Vittorio
Borzì, Alfio
Optimization and Control
Functional Analysis
49M15, 65H04, 65H10, 90C30, 47H05
This work presents a theoretical and numerical investigation of the symplectic gradient adjustment (SGA) method and of a low-rank SGA (LRSGA) method for efficiently solving two-objective optimization problems in the framework of Nash games. The SGA method outperforms the gradient method by including second-order mixed derivatives computed at each iterate, which requires considerably larger computational effort. For this reason, a LRSGA method is proposed where the approximation to second-order mixed derivatives are obtained by rank-one updates. The theoretical analysis presented in this work focuses on novel convergence estimates for the SGA and LRSGA methods, including parameter bounds. The superior computational complexity of the LRSGA method is demonstrated in the training of a CLIP neural architecture, where the LRSGA method outperforms the SGA method by orders of magnitude smaller CPU time.
title A Low-Rank Symplectic Gradient Adjustment Method for Computing Nash Equilibria
topic Optimization and Control
Functional Analysis
49M15, 65H04, 65H10, 90C30, 47H05
url https://arxiv.org/abs/2510.25716