Convergence Rate of Learning a Strongly Variationally Stable Equilibrium

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tatarenko, Tatiana, Kamgarpour, Maryam
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909133986332672
author Tatarenko, Tatiana
Kamgarpour, Maryam
author_facet Tatarenko, Tatiana
Kamgarpour, Maryam
contents We derive the rate of convergence to the strongly variationally stable Nash equilibrium in a convex game, for a zeroth-order learning algorithm. Though we do not assume strong monotonicity of the game, our rates for the one-point feedback and for the two-point feedback match the best known rates for strongly monotone games under zeroth-order information.
format Preprint
id arxiv_https___arxiv_org_abs_2304_02355
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Convergence Rate of Learning a Strongly Variationally Stable Equilibrium
Tatarenko, Tatiana
Kamgarpour, Maryam
Optimization and Control
We derive the rate of convergence to the strongly variationally stable Nash equilibrium in a convex game, for a zeroth-order learning algorithm. Though we do not assume strong monotonicity of the game, our rates for the one-point feedback and for the two-point feedback match the best known rates for strongly monotone games under zeroth-order information.
title Convergence Rate of Learning a Strongly Variationally Stable Equilibrium
topic Optimization and Control
url https://arxiv.org/abs/2304.02355