Cargando…

Local convergence of tensor methods

In this paper, we study local convergence of high-order Tensor Methods for solving convex optimization problems with composite objective. We justify local superlinear convergence under the assumption of uniform convexity of the smooth component, having Lipschitz-continuous high-order derivative. The...

Descripción completa

Detalles Bibliográficos
Autores principales: Doikov, Nikita, Nesterov, Yurii
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Berlin Heidelberg 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9038832/
https://www.ncbi.nlm.nih.gov/pubmed/35535049
http://dx.doi.org/10.1007/s10107-020-01606-x
_version_ 1784693990428246016
author Doikov, Nikita
Nesterov, Yurii
author_facet Doikov, Nikita
Nesterov, Yurii
author_sort Doikov, Nikita
collection PubMed
description In this paper, we study local convergence of high-order Tensor Methods for solving convex optimization problems with composite objective. We justify local superlinear convergence under the assumption of uniform convexity of the smooth component, having Lipschitz-continuous high-order derivative. The convergence both in function value and in the norm of minimal subgradient is established. Global complexity bounds for the Composite Tensor Method in convex and uniformly convex cases are also discussed. Lastly, we show how local convergence of the methods can be globalized using the inexact proximal iterations.
format Online
Article
Text
id pubmed-9038832
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Springer Berlin Heidelberg
record_format MEDLINE/PubMed
spelling pubmed-90388322022-05-07 Local convergence of tensor methods Doikov, Nikita Nesterov, Yurii Math Program Full Length Paper In this paper, we study local convergence of high-order Tensor Methods for solving convex optimization problems with composite objective. We justify local superlinear convergence under the assumption of uniform convexity of the smooth component, having Lipschitz-continuous high-order derivative. The convergence both in function value and in the norm of minimal subgradient is established. Global complexity bounds for the Composite Tensor Method in convex and uniformly convex cases are also discussed. Lastly, we show how local convergence of the methods can be globalized using the inexact proximal iterations. Springer Berlin Heidelberg 2021-01-04 2022 /pmc/articles/PMC9038832/ /pubmed/35535049 http://dx.doi.org/10.1007/s10107-020-01606-x Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Full Length Paper
Doikov, Nikita
Nesterov, Yurii
Local convergence of tensor methods
title Local convergence of tensor methods
title_full Local convergence of tensor methods
title_fullStr Local convergence of tensor methods
title_full_unstemmed Local convergence of tensor methods
title_short Local convergence of tensor methods
title_sort local convergence of tensor methods
topic Full Length Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9038832/
https://www.ncbi.nlm.nih.gov/pubmed/35535049
http://dx.doi.org/10.1007/s10107-020-01606-x
work_keys_str_mv AT doikovnikita localconvergenceoftensormethods
AT nesterovyurii localconvergenceoftensormethods