Saved in:
Bibliographic Details
Main Authors: Xu, Meng, Jiang, Bo, Liu, Ya-Feng, So, Anthony Man-Cho
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.00482
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909332473380864
author Xu, Meng
Jiang, Bo
Liu, Ya-Feng
So, Anthony Man-Cho
author_facet Xu, Meng
Jiang, Bo
Liu, Ya-Feng
So, Anthony Man-Cho
contents In this paper, we establish for the first time the oracle complexity of a Riemannian inexact augmented Lagrangian (RiAL) method with the classical dual update for solving a class of Riemannian nonsmooth composite problems. By using the Riemannian gradient descent method with a specified stopping criterion for solving the inner subproblem, we show that the RiAL method can find an $\varepsilon$-stationary point of the considered problem with $\mathcal{O}(\varepsilon^{-3})$ calls to the first-order oracle. This achieves the best oracle complexity known to date. Numerical results demonstrate that the use of the classical dual stepsize is crucial to the high efficiency of the RiAL method.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00482
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Oracle Complexity of a Riemannian Inexact Augmented Lagrangian Method for Riemannian Nonsmooth Composite Problems
Xu, Meng
Jiang, Bo
Liu, Ya-Feng
So, Anthony Man-Cho
Optimization and Control
In this paper, we establish for the first time the oracle complexity of a Riemannian inexact augmented Lagrangian (RiAL) method with the classical dual update for solving a class of Riemannian nonsmooth composite problems. By using the Riemannian gradient descent method with a specified stopping criterion for solving the inner subproblem, we show that the RiAL method can find an $\varepsilon$-stationary point of the considered problem with $\mathcal{O}(\varepsilon^{-3})$ calls to the first-order oracle. This achieves the best oracle complexity known to date. Numerical results demonstrate that the use of the classical dual stepsize is crucial to the high efficiency of the RiAL method.
title On the Oracle Complexity of a Riemannian Inexact Augmented Lagrangian Method for Riemannian Nonsmooth Composite Problems
topic Optimization and Control
url https://arxiv.org/abs/2410.00482