Study of the behaviour of Nesterov Accelerated Gradient in a non convex setting: the strongly quasar convex case

Autor:	Hermant, J, Aujol, J. -F, Dossal, C, Rondepierre, A
Rok vydání:	2024
Předmět:	Mathematics - Optimization and Control
Druh dokumentu:	Working Paper
Popis:	We study the convergence of Nesterov Accelerated Gradient (NAG) minimization algorithm applied to a class of non convex functions called strongly quasar convex functions, which can exhibit highly non convex behaviour. We show that in the case of strongly quasar convex functions, NAG can achieve an accelerated convergence speed at the cost of a lower curvature assumption. We provide a continuous analysis through high resolution ODEs, in which negative friction may appear. Finally, we investigate connections with a weaker class of non convex functions (smooth Polyak-\L ojasiewicz functions) by characterizing the gap between this class and the one of smooth strongly quasar convex functions.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.19809 Zobrazit plný text záznamu View this record from Arxiv