Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization

(1, 2, 3) , (1, 2, 3)
1
2
3

Abstract

Although ADAM is a very popular algorithm for optimizing the weights of neural networks, it has been recently shown that it can diverge even in simple convex optimization examples. Several variants of ADAM have been proposed to circumvent this convergence issue. In this work, we study the ADAM algorithm for smooth nonconvex optimization under a boundedness assumption on the adaptive learning rate. The bound on the adaptive step size depends on the Lipschitz constant of the gradient of the objective function and provides safe theoretical adaptive step sizes. Under this boundedness assumption, we show a novel first order convergence rate result in both deterministic and stochastic contexts. Furthermore, we establish convergence rates of the function value sequence using the Kurdyka-Łojasiewicz property.
Fichier principal
Vignette du fichier
barakat20a.pdf (569.66 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-02366337 , version 1 (15-11-2019)
hal-02366337 , version 2 (18-11-2022)

Identifiers

Cite

Anas Barakat, Pascal Bianchi. Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization. Asian Conference on Machine Learning, Nov 2020, Bangkok, Thailand. ⟨hal-02366337v2⟩
55 View
97 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More