Estimation of matrices with row sparsity

O. Klopp; A. B. Tsybakov

doi:10.1134/S0032946015040031

Estimation of matrices with row sparsity

O. Klopp
, A. B. Tsybakov

Université Paris-Nanterre
ENSAE

Research output: Contribution to journal › Article › peer-review

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.

Original language	English
Pages (from-to)	335-348
Number of pages	14
Journal	Problems of Information Transmission
Volume	51
Issue number	4
DOIs	https://doi.org/10.1134/S0032946015040031
Publication status	Published - 1 Oct 2015
Externally published	Yes

Access to Document

10.1134/S0032946015040031

Cite this

@article{d77e2912ffa049c9a7ac8c000cebf459,

title = "Estimation of matrices with row sparsity",

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.",

author = "O. Klopp and Tsybakov, \{A. B.\}",

note = "Publisher Copyright: {\textcopyright} 2015, Pleiades Publishing, Inc.",

year = "2015",

month = oct,

day = "1",

doi = "10.1134/S0032946015040031",

language = "English",

volume = "51",

pages = "335--348",

journal = "Problems of Information Transmission",

issn = "0032-9460",

number = "4",

}

TY - JOUR

T1 - Estimation of matrices with row sparsity

AU - Klopp, O.

AU - Tsybakov, A. B.

PY - 2015/10/1

Y1 - 2015/10/1

N2 - 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.

AB - 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.

U2 - 10.1134/S0032946015040031

DO - 10.1134/S0032946015040031

M3 - Article

AN - SCOPUS:84952939495

SN - 0032-9460

VL - 51

SP - 335

EP - 348

JO - Problems of Information Transmission

JF - Problems of Information Transmission

IS - 4

ER -

Estimation of matrices with row sparsity

Abstract

Access to Document

Fingerprint

Cite this