Stochastic optimization over proximally smooth sets

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Davis, Damek, Drusvyatskiy, Dmitriy, Shi, Zhan
Formato: Preprint
Publicado: 2020
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910790505725952
author Davis, Damek
Drusvyatskiy, Dmitriy
Shi, Zhan
author_facet Davis, Damek
Drusvyatskiy, Dmitriy
Shi, Zhan
contents We introduce a class of stochastic algorithms for minimizing weakly convex functions over proximally smooth sets. As their main building blocks, the algorithms use simplified models of the objective function and the constraint set, along with a retraction operation to restore feasibility. All the proposed methods come equipped with a finite time efficiency guarantee in terms of a natural stationarity measure. We discuss consequences for nonsmooth optimization over smooth manifolds and over sets cut out by weakly-convex inequalities.
format Preprint
id arxiv_https___arxiv_org_abs_2002_06309
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Stochastic optimization over proximally smooth sets
Davis, Damek
Drusvyatskiy, Dmitriy
Shi, Zhan
Optimization and Control
65K05, 65K10, 90C15, 90C30
We introduce a class of stochastic algorithms for minimizing weakly convex functions over proximally smooth sets. As their main building blocks, the algorithms use simplified models of the objective function and the constraint set, along with a retraction operation to restore feasibility. All the proposed methods come equipped with a finite time efficiency guarantee in terms of a natural stationarity measure. We discuss consequences for nonsmooth optimization over smooth manifolds and over sets cut out by weakly-convex inequalities.
title Stochastic optimization over proximally smooth sets
topic Optimization and Control
65K05, 65K10, 90C15, 90C30
url https://arxiv.org/abs/2002.06309