Symplectic Discretization Approach for Developing New Proximal Point Algorithm

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yuan, Ya-xiang, Zhang, Yi
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913570905653248
author Yuan, Ya-xiang
Zhang, Yi
author_facet Yuan, Ya-xiang
Zhang, Yi
contents The rapid advancements in high-dimensional statistics and machine learning have increased the use of first-order methods. Many of these methods can be regarded as instances of the proximal point algorithm. Given the importance of the proximal point algorithm, there has been growing interest in developing its accelerated variants. However, some existing accelerated proximal point algorithms exhibit oscillatory behavior, which can impede their numerical convergence rate. In this paper, we first introduce an ODE system and demonstrate its \( o(1/t^2) \) convergence rate and weak convergence property. Next, we apply the Symplectic Euler Method to discretize the ODE and obtain a new accelerated proximal point algorithm, which we call the Symplectic Proximal Point Algorithm. The reason for using the Symplectic Euler Method is its ability to preserve the geometric structure of the ODEs. Theoretically, we demonstrate that the Symplectic Proximal Point Algorithm achieves an \( o(1/k^2) \) convergence rate and that the sequences generated by our method converge weakly to the solution set. Practically, our numerical experiments illustrate that the Symplectic Proximal Point Algorithm significantly reduces oscillatory behavior, leading to improved long-time behavior and faster numerical convergence rate.
format Preprint
id arxiv_https___arxiv_org_abs_2308_03986
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Symplectic Discretization Approach for Developing New Proximal Point Algorithm
Yuan, Ya-xiang
Zhang, Yi
Optimization and Control
47J20, 47H05, 65K15, 65Y20, 90C25, 90C52
The rapid advancements in high-dimensional statistics and machine learning have increased the use of first-order methods. Many of these methods can be regarded as instances of the proximal point algorithm. Given the importance of the proximal point algorithm, there has been growing interest in developing its accelerated variants. However, some existing accelerated proximal point algorithms exhibit oscillatory behavior, which can impede their numerical convergence rate. In this paper, we first introduce an ODE system and demonstrate its \( o(1/t^2) \) convergence rate and weak convergence property. Next, we apply the Symplectic Euler Method to discretize the ODE and obtain a new accelerated proximal point algorithm, which we call the Symplectic Proximal Point Algorithm. The reason for using the Symplectic Euler Method is its ability to preserve the geometric structure of the ODEs. Theoretically, we demonstrate that the Symplectic Proximal Point Algorithm achieves an \( o(1/k^2) \) convergence rate and that the sequences generated by our method converge weakly to the solution set. Practically, our numerical experiments illustrate that the Symplectic Proximal Point Algorithm significantly reduces oscillatory behavior, leading to improved long-time behavior and faster numerical convergence rate.
title Symplectic Discretization Approach for Developing New Proximal Point Algorithm
topic Optimization and Control
47J20, 47H05, 65K15, 65Y20, 90C25, 90C52
url https://arxiv.org/abs/2308.03986