Gradient correlation is needed to accelerate SGD with momentum - Archive ouverte HAL
Preprints, Working Papers, ... Year : 2024

Gradient correlation is needed to accelerate SGD with momentum

Abstract

Empirically, it has been observed that adding momentum to Stochastic Gradient Descent (SGD) accelerates the convergence of the algorithm. However, the literature has been rather pessimistic, even in the case of convex functions, about the possibility of theoretically proving this observation. We investigate the possibility of obtaining accelerated convergence of the Stochastic Nesterov Accelerated Gradient (SNAG), a momentum-based version of SGD, when minimizing a sum of functions in a convex setting. We demonstrate that the average correlation between gradients allows to verify the strong growth condition, which is the key ingredient to obtain acceleration with SNAG. Numerical experiments, both in linear regression and deep neural network optimization, confirm in practice our theoretical results.
Fichier principal
Vignette du fichier
racoga_arxiv.pdf (1.95 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04728121 , version 1 (09-10-2024)

Identifiers

  • HAL Id : hal-04728121 , version 1

Cite

Julien Hermant, Marien Renaud, Jean-François Aujol, Charles Dossal, Aude Rondepierre. Gradient correlation is needed to accelerate SGD with momentum. 2024. ⟨hal-04728121⟩
42 View
8 Download

Share

More