Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sakai, Hiroyuki, Iiduka, Hideaki
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.00859
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915148707397632
author Sakai, Hiroyuki
Iiduka, Hideaki
author_facet Sakai, Hiroyuki
Iiduka, Hideaki
contents This paper proposes a general framework of Riemannian adaptive optimization methods. The framework encapsulates several stochastic optimization algorithms on Riemannian manifolds and incorporates the mini-batch strategy that is often used in deep learning. Within this framework, we also propose AMSGrad on embedded submanifolds of Euclidean space. Moreover, we give convergence analyses valid for both a constant and a diminishing step size. Our analyses also reveal the relationship between the convergence rate and mini-batch size. In numerical experiments, we applied the proposed algorithm to principal component analysis and the low-rank matrix completion problem, which can be considered to be Riemannian optimization problems. Python implementations of the methods used in the numerical experiments are available at https://github.com/iiduka-researches/202408-adaptive.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00859
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A general framework of Riemannian adaptive optimization methods with a convergence analysis
Sakai, Hiroyuki
Iiduka, Hideaki
Optimization and Control
65k05, 90C25, 57R25
G.1.6
This paper proposes a general framework of Riemannian adaptive optimization methods. The framework encapsulates several stochastic optimization algorithms on Riemannian manifolds and incorporates the mini-batch strategy that is often used in deep learning. Within this framework, we also propose AMSGrad on embedded submanifolds of Euclidean space. Moreover, we give convergence analyses valid for both a constant and a diminishing step size. Our analyses also reveal the relationship between the convergence rate and mini-batch size. In numerical experiments, we applied the proposed algorithm to principal component analysis and the low-rank matrix completion problem, which can be considered to be Riemannian optimization problems. Python implementations of the methods used in the numerical experiments are available at https://github.com/iiduka-researches/202408-adaptive.
title A general framework of Riemannian adaptive optimization methods with a convergence analysis
topic Optimization and Control
65k05, 90C25, 57R25
G.1.6
url https://arxiv.org/abs/2409.00859