Stochastic optimization over expectation-formulated generalized Stiefel manifold

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Linshuo, Xiao, Nachuan, Liu, Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929651135283200
author Jiang, Linshuo
Xiao, Nachuan
Liu, Xin
author_facet Jiang, Linshuo
Xiao, Nachuan
Liu, Xin
contents In this paper, we consider a class of stochastic optimization problems over the expectation-formulated generalized Stiefel manifold (SOEGS), where the objective function $f$ is continuously differentiable. We propose a novel constraint dissolving penalty function with a customized penalty term (CDFDP), which maintains the same order of differentiability as $f$. Our theoretical analysis establishes the global equivalence between CDFCP and SOEGS in the sense that they share the same first-order and second-order stationary points under mild conditions. These results on equivalence enable the direct implementation of various stochastic optimization approaches to solve SOEGS. In particular, we develop a stochastic gradient algorithm and its accelerated variant by incorporating an adaptive step size strategy. Furthermore, we prove their $\mathcal{O}(\varepsilon^{-4})$ sample complexity for finding an $\varepsilon$-stationary point of CDFCP. Comprehensive numerical experiments show the efficiency and robustness of our proposed algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20008
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stochastic optimization over expectation-formulated generalized Stiefel manifold
Jiang, Linshuo
Xiao, Nachuan
Liu, Xin
Optimization and Control
In this paper, we consider a class of stochastic optimization problems over the expectation-formulated generalized Stiefel manifold (SOEGS), where the objective function $f$ is continuously differentiable. We propose a novel constraint dissolving penalty function with a customized penalty term (CDFDP), which maintains the same order of differentiability as $f$. Our theoretical analysis establishes the global equivalence between CDFCP and SOEGS in the sense that they share the same first-order and second-order stationary points under mild conditions. These results on equivalence enable the direct implementation of various stochastic optimization approaches to solve SOEGS. In particular, we develop a stochastic gradient algorithm and its accelerated variant by incorporating an adaptive step size strategy. Furthermore, we prove their $\mathcal{O}(\varepsilon^{-4})$ sample complexity for finding an $\varepsilon$-stationary point of CDFCP. Comprehensive numerical experiments show the efficiency and robustness of our proposed algorithms.
title Stochastic optimization over expectation-formulated generalized Stiefel manifold
topic Optimization and Control
url https://arxiv.org/abs/2412.20008