EUVIMEDEUVIMED entdecken
Crossref

Acceleration Methods

Alexandre d’Aspremont, Damien Scieur, Adrien Taylor

Foundations and Trends® in Optimization · 2021

DOI: 10.1561/2400000036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Foundations and Trends® in Optimization, 2021. Verfasst von Alexandre d’Aspremont und 2 weiteren Autor:innen. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 283 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This monograph covers some recent advances in a range of acceleration techniques frequently used in convex optimization. We first use quadratic optimization problems to introduce two key families of methods, namely momentum and nested optimization schemes. They coincide in the quadratic case to form the Chebyshev method. We discuss momentum methods in detail, starting with the seminal work of Nesterov [1] and structure convergence proofs using a few master templates, such as that for optimized gradient methods, which provide the key benefit of showing how momentum methods optimize convergence guarantees. We further cover proximal acceleration, at the heart of the Catalyst and Accelerated Hybrid Proximal Extragradient frameworks, using similar algorithmic patterns. Common acceleration techniques rely directly on the knowledge of some of the regularity parameters in the problem at hand. We conclude by discussing restart schemes, a set of simple techniques for reaching nearly optimal convergence rates while adapting to unobserved regularity parameters.

Zitieren

APA

d’Aspremont, A., Scieur, D., & Taylor, A. (2021). Acceleration Methods. Foundations and Trends® in Optimization. https://doi.org/10.1561/2400000036

Vancouver

d’Aspremont A, Scieur D, Taylor A. Acceleration Methods. Foundations and Trends® in Optimization. 2021. doi:10.1561/2400000036

BibTeX
@article{dAspremont2021,
  author = {d’Aspremont, Alexandre and Scieur, Damien and Taylor, Adrien},
  title = {Acceleration Methods},
  journal = {Foundations and Trends® in Optimization},
  year = {2021},
  doi = {10.1561/2400000036}
}
Kostenlos starten →