Guardado en:
Detalles Bibliográficos
Autores principales: Foglia, Katherine Rossella, Pisani, Francesco Sergio, Colao, Vittorio
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.26983
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908761033015296
author Foglia, Katherine Rossella
Pisani, Francesco Sergio
Colao, Vittorio
author_facet Foglia, Katherine Rossella
Pisani, Francesco Sergio
Colao, Vittorio
contents We introduce LMLRSGA, a limited memory variant of Low Rank Symplectic Gradient Adjustment (LRSGA) for differentiable games. It is an iterative scheme for approximating Nash equilibria with first order like cost while retaining the stabilizing effect of symplectic second order corrections via low rank information. By storing only a limited history of curvature pairs, LMLRSGA is well suited to high parameter competitive models such as GANs. In particular, we provide a per iteration spectral stability condition for LRSGA near Nash equilibria, a limited memory implementation (LMLRSGA) based on adapted two loop recursions together with a local convergence analysis for fixed history length, and an empirical evaluation on GAN training on MNIST and FashionMNIST, including spectral diagnostics of the training dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Limited-Memory LRSGA: An Iterative Method for Computing Nash Equilibria in Competitive Optimization Problems
Foglia, Katherine Rossella
Pisani, Francesco Sergio
Colao, Vittorio
Optimization and Control
We introduce LMLRSGA, a limited memory variant of Low Rank Symplectic Gradient Adjustment (LRSGA) for differentiable games. It is an iterative scheme for approximating Nash equilibria with first order like cost while retaining the stabilizing effect of symplectic second order corrections via low rank information. By storing only a limited history of curvature pairs, LMLRSGA is well suited to high parameter competitive models such as GANs. In particular, we provide a per iteration spectral stability condition for LRSGA near Nash equilibria, a limited memory implementation (LMLRSGA) based on adapted two loop recursions together with a local convergence analysis for fixed history length, and an empirical evaluation on GAN training on MNIST and FashionMNIST, including spectral diagnostics of the training dynamics.
title Limited-Memory LRSGA: An Iterative Method for Computing Nash Equilibria in Competitive Optimization Problems
topic Optimization and Control
url https://arxiv.org/abs/2510.26983