.png){kind=icon}
.png){kind=icon}
Return
Nonsmooth Optimization over the Stiefel Manifold and Beyond: Proximal Gradient Method and Recent Variants
.png){kind=icon}
PRE
AI
S
S
A
T
DOI：10.1137/24M1628578.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We consider optimization problems over the Stiefel manifold whose objective function is the summation of a smooth function and a nonsmooth function. Existing methods for solving this class of problems converge slowly in practice, involve subproblems that can be as difficult as the original problem, or lack rigorous convergence guarantees. In this paper, we propose a manifold proximal gradient method (ManPG) for solving this class of problems. We prove that the proposed method converges globally to a stationary point and establish its iteration complexity for obtaining an \epsilon -stationary point. Furthermore, we present numerical results on the sparse PCA and compressed modes problems to demonstrate the advantages of the proposed method. We also discuss some recent advances related to ManPG for Riemannian optimization with nonsmooth objective functions.
Keywords:
manifold optimization
Stiefel manifold
nonsmooth
proximal gradient method
iteration complexity
semismooth Newton method
stochastic algorithms
zeroth-order algorithms
Journal
IF:
6.1
Papers:
888
Citations:
1.2W
Organization
Cited Papers