This article is cited in 4 papers

Methods of Signal Processing

Estimation of matrices with row sparsity

O. Klopp^a, A. B. Tsybakov<sup>b

a</sup> CREST and MODAL'X, University Paris Ouest, Nanterre, France
^b UMR CNRS 9194, ENSAE, Malakoff, France

Abstract: An increasing number of applications is concerned with recovering a sparse matrix from noisy observations. In this paper, we consider the setting where each row of an unknown matrix is sparse. We establish minimax optimal rates of convergence for estimating matrices with row sparsity. A major focus in the present paper is on the derivation of lower bounds.

UDC: 621.391.1+519.2

Received: 15.03.2015
Revised: 08.09.2015

 English version: Problems of Information Transmission, 2015, 51:4, 335–348

Bibliographic databases:

• 
•