Saved in:
Bibliographic Details
Main Authors: Yang, Yan, Gao, Bin, Yuan, Ya-xiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.13830
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909815722213376
author Yang, Yan
Gao, Bin
Yuan, Ya-xiang
author_facet Yang, Yan
Gao, Bin
Yuan, Ya-xiang
contents Imposing additional constraints on low-rank optimization has garnered growing interest. However, the geometry of coupled constraints hampers the well-developed low-rank structure and makes the problem intricate. To this end, we propose a space-decoupling framework for optimization on bounded-rank matrices with orthogonally invariant constraints. The "space-decoupling" is reflected in several ways. We show that the tangent cone of coupled constraints is the intersection of tangent cones of each constraint. Moreover, we decouple the intertwined bounded-rank and orthogonally invariant constraints into two spaces, leading to optimization on a smooth manifold. Implementing Riemannian algorithms on this manifold is painless as long as the geometry of additional constraints is known. In addition, we unveil the equivalence between the reformulated problem and the original problem. Numerical experiments on real-world applications -- spherical data fitting, graph similarity measuring, low-rank SDP, model reduction of Markov processes, reinforcement learning, and deep learning -- validate the superiority of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13830
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A space-decoupling framework for optimization on bounded-rank matrices with orthogonally invariant constraints
Yang, Yan
Gao, Bin
Yuan, Ya-xiang
Optimization and Control
Artificial Intelligence
Machine Learning
Imposing additional constraints on low-rank optimization has garnered growing interest. However, the geometry of coupled constraints hampers the well-developed low-rank structure and makes the problem intricate. To this end, we propose a space-decoupling framework for optimization on bounded-rank matrices with orthogonally invariant constraints. The "space-decoupling" is reflected in several ways. We show that the tangent cone of coupled constraints is the intersection of tangent cones of each constraint. Moreover, we decouple the intertwined bounded-rank and orthogonally invariant constraints into two spaces, leading to optimization on a smooth manifold. Implementing Riemannian algorithms on this manifold is painless as long as the geometry of additional constraints is known. In addition, we unveil the equivalence between the reformulated problem and the original problem. Numerical experiments on real-world applications -- spherical data fitting, graph similarity measuring, low-rank SDP, model reduction of Markov processes, reinforcement learning, and deep learning -- validate the superiority of the proposed framework.
title A space-decoupling framework for optimization on bounded-rank matrices with orthogonally invariant constraints
topic Optimization and Control
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2501.13830