PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Goujaud, Baptiste, Moucer, Céline, Glineur, François, Hendrickx, Julien, Taylor, Adrien, Dieuleveut, Aymeric
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913392757833728
author Goujaud, Baptiste
Moucer, Céline
Glineur, François
Hendrickx, Julien
Taylor, Adrien
Dieuleveut, Aymeric
author_facet Goujaud, Baptiste
Moucer, Céline
Glineur, François
Hendrickx, Julien
Taylor, Adrien
Dieuleveut, Aymeric
contents PEPit is a Python package aiming at simplifying the access to worst-case analyses of a large family of first-order optimization methods possibly involving gradient, projection, proximal, or linear optimization oracles, along with their approximate, or Bregman variants. In short, PEPit is a package enabling computer-assisted worst-case analyses of first-order optimization methods. The key underlying idea is to cast the problem of performing a worst-case analysis, often referred to as a performance estimation problem (PEP), as a semidefinite program (SDP) which can be solved numerically. To do that, the package users are only required to write first-order methods nearly as they would have implemented them. The package then takes care of the SDP modeling parts, and the worst-case analysis is performed numerically via a standard solver.
format Preprint
id arxiv_https___arxiv_org_abs_2201_04040
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
Goujaud, Baptiste
Moucer, Céline
Glineur, François
Hendrickx, Julien
Taylor, Adrien
Dieuleveut, Aymeric
Optimization and Control
Machine Learning
Mathematical Software
Numerical Analysis
PEPit is a Python package aiming at simplifying the access to worst-case analyses of a large family of first-order optimization methods possibly involving gradient, projection, proximal, or linear optimization oracles, along with their approximate, or Bregman variants. In short, PEPit is a package enabling computer-assisted worst-case analyses of first-order optimization methods. The key underlying idea is to cast the problem of performing a worst-case analysis, often referred to as a performance estimation problem (PEP), as a semidefinite program (SDP) which can be solved numerically. To do that, the package users are only required to write first-order methods nearly as they would have implemented them. The package then takes care of the SDP modeling parts, and the worst-case analysis is performed numerically via a standard solver.
title PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
topic Optimization and Control
Machine Learning
Mathematical Software
Numerical Analysis
url https://arxiv.org/abs/2201.04040