Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion
Preprint
Abstract
We study the robust matrix completion problem for the low-rank Hankel matrix, which detects the sparse corruptions caused by extreme outliers while we try to recover the original Hankel matrix from the partial observation. In this paper, we explore the convenient Hankel structure and propose a novel non-convex algorithm, coined Hankel Structured Gradient Descent (HSGD), for large-scale robust Hankel matrix completion problems. HSGD is highly computing- and sample-efficient compared to the state-of-the-arts. The recovery guarantee with a linear convergence rate has been established for HSGD under some mild assumptions. The empirical advantages of HSGD are verified on both synthetic datasets and real-world nuclear magnetic resonance signals.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Exact matrix completion based on low rank Hankel structure in the Fourier domainApplied and Computational Harmonic Analysis, 2021
- Rapid Robust Principal Component Analysis: CUR Accelerated Inexact Low Rank EstimationIEEE Signal Processing Letters, 2020
- Structured Low-Rank Algorithms: Theory, Magnetic Resonance Applications, and Links to Machine LearningIEEE Signal Processing Magazine, 2020
- Fast and provable algorithms for spectrally sparse signal reconstruction via low-rank Hankel matrix completionApplied and Computational Harmonic Analysis, 2019
- MUSIC for single-snapshot spectral estimation: Stability and super-resolutionApplied and Computational Harmonic Analysis, 2016
- Accelerated NMR Spectroscopy with Low‐Rank ReconstructionAngewandte Chemie International Edition, 2014
- Denoising MR Spectroscopic Imaging Data With Low-Rank ApproximationsIEEE Transactions on Biomedical Engineering, 2013
- User-Friendly Tail Bounds for Sums of Random MatricesFoundations of Computational Mathematics, 2011
- Fast Multidimensional NMR Spectroscopy Using Compressed SensingAngewandte Chemie International Edition, 2011
- Exact Matrix Completion via Convex OptimizationFoundations of Computational Mathematics, 2009