Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Chenhao, Hong, Yusu, Lin, Junhong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.11125
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916627108331520
author Yu, Chenhao
Hong, Yusu
Lin, Junhong
author_facet Yu, Chenhao
Hong, Yusu
Lin, Junhong
contents We investigate the Randomized Stochastic Accelerated Gradient (RSAG) method, utilizing either constant or adaptive step sizes, for stochastic optimization problems with generalized smooth objective functions. Under relaxed affine variance assumptions for the stochastic gradient noise, we establish high-probability convergence rates of order $\tilde{O}\left(\sqrt{\log(1/δ)/T}\right)$ for function value gaps in the convex setting, and for the squared gradient norms in the non-convex setting. Furthermore, when the noise parameters are sufficiently small, the convergence rate improves to $\tilde{O}\left(\log(1/δ)/T\right)$, where $T$ denotes the total number of iterations and $δ$ is the probability margin. Our analysis is also applicable to SGD with both constant and adaptive step sizes.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence Analysis of Stochastic Accelerated Gradient Methods for Generalized Smooth Optimizations
Yu, Chenhao
Hong, Yusu
Lin, Junhong
Optimization and Control
We investigate the Randomized Stochastic Accelerated Gradient (RSAG) method, utilizing either constant or adaptive step sizes, for stochastic optimization problems with generalized smooth objective functions. Under relaxed affine variance assumptions for the stochastic gradient noise, we establish high-probability convergence rates of order $\tilde{O}\left(\sqrt{\log(1/δ)/T}\right)$ for function value gaps in the convex setting, and for the squared gradient norms in the non-convex setting. Furthermore, when the noise parameters are sufficiently small, the convergence rate improves to $\tilde{O}\left(\log(1/δ)/T\right)$, where $T$ denotes the total number of iterations and $δ$ is the probability margin. Our analysis is also applicable to SGD with both constant and adaptive step sizes.
title Convergence Analysis of Stochastic Accelerated Gradient Methods for Generalized Smooth Optimizations
topic Optimization and Control
url https://arxiv.org/abs/2502.11125