3 papers
cs.LG2025
Global Convergence Analysis of Vanilla Gradient Descent for Asymmetric Matrix Completion
Xu Zhang, Shuo Chen, Jinsheng Li +2
This paper investigates the asymmetric low-rank matrix completion problem, which can be formulated as an unconstrained non-convex optimization problem with a nonlinear least-square…
cs.IT2025
Fast and Provable Hankel Tensor Completion for Multi-measurement Spectral Compressed Sensing
Jinsheng Li, Xu Zhang, Shuang Wu +1
In this paper, we introduce a novel low-rank Hankel tensor completion approach to address the problem of multi-measurement spectral compressed sensing. By lifting the multiple sign…
cs.IT2024
Simpler Gradient Methods for Blind Super-Resolution with Lower Iteration Complexity
Jinsheng Li, Wei Cui, Xu Zhang
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…