Parametric complexity analysis for a class of first-order Adagrad-like algorithms - Algorithmes Parallèles et Optimisation Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Parametric complexity analysis for a class of first-order Adagrad-like algorithms

Résumé

A class of algorithms for optimization in the presence of noise is presented, that does not require the evaluation of the objective function. This class generalizes the well-known Adagrad method. The complexity of this class is then analyzed as a function of its parameters, and it is shown that some methods of the class enjoy a better asymptotic convergence rate than previously known. A new class of algorithms is then derived with similar characteristics. Initial numerical experiments suggest that it may have some merits in practice.

Dates et versions

hal-03718810 , version 1 (09-07-2022)

Licence

Paternité

Identifiants

Citer

Serge Gratton, Sadok Jerad, Philippe L. Toint. Parametric complexity analysis for a class of first-order Adagrad-like algorithms. 2022. ⟨hal-03718810⟩
49 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More