Guardado en:
Detalles Bibliográficos
Autores principales: Davydov, Alexander, Jafarpour, Saber, Proskurnikov, Anton V., Bullo, Francesco
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2303.11273
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916912363995136
author Davydov, Alexander
Jafarpour, Saber
Proskurnikov, Anton V.
Bullo, Francesco
author_facet Davydov, Alexander
Jafarpour, Saber
Proskurnikov, Anton V.
Bullo, Francesco
contents While monotone operator theory is often studied on Hilbert spaces, many interesting problems in machine learning and optimization arise naturally in finite-dimensional vector spaces endowed with non-Euclidean norms, such as diagonally-weighted $\ell_{1}$ or $\ell_{\infty}$ norms. This paper provides a natural generalization of monotone operator theory to finite-dimensional non-Euclidean spaces. The key tools are weak pairings and logarithmic norms. We show that the resolvent and reflected resolvent operators of non-Euclidean monotone mappings exhibit similar properties to their counterparts in Hilbert spaces. Furthermore, classical iterative methods and splitting methods for finding zeros of monotone operators are shown to converge in the non-Euclidean case. We apply our theory to equilibrium computation and Lipschitz constant estimation of recurrent neural networks, obtaining novel iterations and tighter upper bounds via forward-backward splitting.
format Preprint
id arxiv_https___arxiv_org_abs_2303_11273
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Non-Euclidean Monotone Operator Theory and Applications
Davydov, Alexander
Jafarpour, Saber
Proskurnikov, Anton V.
Bullo, Francesco
Optimization and Control
While monotone operator theory is often studied on Hilbert spaces, many interesting problems in machine learning and optimization arise naturally in finite-dimensional vector spaces endowed with non-Euclidean norms, such as diagonally-weighted $\ell_{1}$ or $\ell_{\infty}$ norms. This paper provides a natural generalization of monotone operator theory to finite-dimensional non-Euclidean spaces. The key tools are weak pairings and logarithmic norms. We show that the resolvent and reflected resolvent operators of non-Euclidean monotone mappings exhibit similar properties to their counterparts in Hilbert spaces. Furthermore, classical iterative methods and splitting methods for finding zeros of monotone operators are shown to converge in the non-Euclidean case. We apply our theory to equilibrium computation and Lipschitz constant estimation of recurrent neural networks, obtaining novel iterations and tighter upper bounds via forward-backward splitting.
title Non-Euclidean Monotone Operator Theory and Applications
topic Optimization and Control
url https://arxiv.org/abs/2303.11273