Work

Rate Optimal Denoising of Simultaneously Sparse and Low Rank Matrices

Year: 2014

Type: preprint

Abstract: We study minimax rates for denoising simultaneously sparse and low rank matrices in high dimensions. We show that an iterative thresholding algorithm achieves (near) optimal rates adaptively under mild conditions for a large class of loss functions. Numerical experiments on synthetic datasets also demonstrate the competitive performance of the proposed method.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1405.0338

Authors: Yang, Dan, Ma, Zongming, Buja, Andreas

Institutions: Rutgers, The State University of New Jersey, University of Pennsylvania

Language: English

Topic: Statistical Methods and Inference

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2999417281

Cites: 38

Cited by: 25

Related to: 10