Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport

In recent years, stochastic variance reduction algorithms have attracted considerable attention for minimizing the average of a large but finite number of loss functions. This paper proposes a novel Riemannian extension of the Euclidean stochastic variance reduced gradient (R-SVRG) algorithm to a ma...

Full description

Bibliographic Details

Published in:	arXiv.org
Main Authors:	Sato, Hiroyuki, Kasai, Hiroyuki, Mishra, Bamdev
Format:	Paper
Language:	English
Published:	Ithaca Cornell University Library, arXiv.org 31.05.2019
Subjects:	Algorithms Convergence Decay rate Euclidean geometry Manifolds (mathematics) Principal components analysis Subspaces
ISSN:	2331-8422
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!