Convergence of Riemannian Stochastic Gradient Descents: Varying Batch Sizes And Nonstandard Batch Forming

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Wu, Hao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910141698277376
author Wu, Hao
author_facet Wu, Hao
contents We establish convergence theorems for Riemannian stochastic gradient descents in which the underlying probability spaces vary from iteration to iteration. As applications, we deduce convergence results for Riemannian stochastic gradient descents with varying batch sizes and unbiased batch forming schemes.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06350
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Convergence of Riemannian Stochastic Gradient Descents: Varying Batch Sizes And Nonstandard Batch Forming
Wu, Hao
Optimization and Control
41A60, 53Z50, 62L20, 68T05
We establish convergence theorems for Riemannian stochastic gradient descents in which the underlying probability spaces vary from iteration to iteration. As applications, we deduce convergence results for Riemannian stochastic gradient descents with varying batch sizes and unbiased batch forming schemes.
title Convergence of Riemannian Stochastic Gradient Descents: Varying Batch Sizes And Nonstandard Batch Forming
topic Optimization and Control
41A60, 53Z50, 62L20, 68T05
url https://arxiv.org/abs/2604.06350