Gradient methods with memory

Yurii Nesterov () and Mihai Florea
Additional contact information
Yurii Nesterov: Université catholique de Louvain, LIDAM/CORE, Belgium
Mihai Florea: Université catholique de Louvain, LIDAM/CORE, Belgium

No 3230, LIDAM Reprints CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE)

Abstract: In this paper, we consider gradient methods for minimizing smooth convex functions, which employ the information obtained at the previous iterations in order to accelerate the convergence towards the optimal solution. This information is used in the form of a piece-wise linear model of the objective function, which provides us with much better prediction abilities as compared with the standard linear model. To the best of our knowledge, this approach was never really applied in Convex Minimization to differentiable functions in view of the high complexity of the corresponding auxiliary problems. However, we show that all necessary computations can be done very efficiently. Consequently, we get new optimization methods, which are better than the usual Gradient Methods both in the number of oracle calls and in the computational time. Our theoretical conclusions are confirmed by preliminary computational experiments.

Keywords: Applied Mathematics; Control and Optimization; Software (search for similar items in EconPapers)
Pages: 18
Date: 2023-01-01
Note: In: Optimization Methods and Software, 2022, vol. 37(3), p. 936-953
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cor:louvrp:3230

DOI: 10.1080/10556788.2020.1858831

Access Statistics for this paper

More papers in LIDAM Reprints CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE) Voie du Roman Pays 34, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Alain GILLIS ().