Saved in:
Bibliographic Details
Main Authors: Li, Jinsheng, Cui, Wei, Zhang, Xu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.18387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912047907733504
author Li, Jinsheng
Cui, Wei
Zhang, Xu
author_facet Li, Jinsheng
Cui, Wei
Zhang, Xu
contents We study the problem of blind super-resolution, which can be formulated as a low-rank matrix recovery problem via vectorized Hankel lift (VHL). The previous gradient descent method based on VHL named PGD-VHL relies on additional regularization such as the projection and balancing penalty, exhibiting a suboptimal iteration complexity. In this paper, we propose a simpler unconstrained optimization problem without the above two types of regularization and develop two new and provable gradient methods named VGD-VHL and ScalGD-VHL. A novel and sharp analysis is provided for the theoretical guarantees of our algorithms, which demonstrates that our methods offer lower iteration complexity than PGD-VHL. In addition, ScalGD-VHL has the lowest iteration complexity while being independent of the condition number. Furthermore, our novel analysis reveals that the blind super-resolution problem is less incoherence-demanding, thereby eliminating the necessity for incoherent projections to achieve linear convergence. Empirical results illustrate that our methods exhibit superior computational efficiency while achieving comparable recovery performance to prior arts.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Simpler Gradient Methods for Blind Super-Resolution with Lower Iteration Complexity
Li, Jinsheng
Cui, Wei
Zhang, Xu
Information Theory
We study the problem of blind super-resolution, which can be formulated as a low-rank matrix recovery problem via vectorized Hankel lift (VHL). The previous gradient descent method based on VHL named PGD-VHL relies on additional regularization such as the projection and balancing penalty, exhibiting a suboptimal iteration complexity. In this paper, we propose a simpler unconstrained optimization problem without the above two types of regularization and develop two new and provable gradient methods named VGD-VHL and ScalGD-VHL. A novel and sharp analysis is provided for the theoretical guarantees of our algorithms, which demonstrates that our methods offer lower iteration complexity than PGD-VHL. In addition, ScalGD-VHL has the lowest iteration complexity while being independent of the condition number. Furthermore, our novel analysis reveals that the blind super-resolution problem is less incoherence-demanding, thereby eliminating the necessity for incoherent projections to achieve linear convergence. Empirical results illustrate that our methods exhibit superior computational efficiency while achieving comparable recovery performance to prior arts.
title Simpler Gradient Methods for Blind Super-Resolution with Lower Iteration Complexity
topic Information Theory
url https://arxiv.org/abs/2409.18387