← Search

Jingkai Yan

2 accepted papers

2021

Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery

NeurIPS 2021poster

We propose a new framework -- Square Root Principal Component Pursuit -- for low-rank matrix recovery from observations corrupted with noise and outliers. Inspired by the square root Lasso, this new formulation does not require prior knowledge of the noise level. We show that a single, universal cho…

Cited by 8SourcePDFScholar