On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems

Abstract

The restricted isometry property (RIP) is a well-known condition that guarantees the absence of spurious local minima in low-rank matrix recovery problems with linear measurements. In this paper, we introduce a novel property named bound difference property (BDP) to study low-rank matrix recovery problems with nonlinear measurements. Using RIP and BDP jointly, we propose a new criterion to certify the nonexistence of spurious local minima in the rank-1 case, and prove that it leads to a much stronger theoretical guarantee than the existing bounds on RIP.

Cite

Text

Bi and Lavaei. "On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems." Artificial Intelligence and Statistics, 2021.

Markdown

[Bi and Lavaei. "On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems." Artificial Intelligence and Statistics, 2021.](https://mlanthology.org/aistats/2021/bi2021aistats-absence/)

BibTeX

@inproceedings{bi2021aistats-absence,
  title     = {{On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems}},
  author    = {Bi, Yingjie and Lavaei, Javad},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2021},
  pages     = {379-387},
  volume    = {130},
  url       = {https://mlanthology.org/aistats/2021/bi2021aistats-absence/}
}