Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion
HanQin Cai, Jian-Feng Cai, Juntao You
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 partial observation. In this paper, we explore the convenient Hankel structure and propose a novel nonconvex 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 art. 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.