A Caltech Library Service

Precise Error Analysis of the ℓ_2-LASSO

Thrampoulidis, Christos and Panahi, Ashkan and Guo, Daniel and Hassibi, Babak (2015) Precise Error Analysis of the ℓ_2-LASSO. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


A classical problem that arises in numerous signal processing applications asks for the reconstruction of an unknown, k-sparse signal x_0∈R^n from underdetermined, noisy, linear measurements y=Ax_0 + z ∈ R^m. One standard approach is to solve the following convex program x^=arg min_x ∥y−Ax∥_2 + λ∥x∥_1, which is known as the ℓ2-LASSO. We assume that the entries of the sensing matrix A and of the noise vector z are i.i.d Gaussian with variances 1/m and σ2. In the large system limit when the problem dimensions grow to infinity, but in constant rates, we precisely characterize the limiting behavior of the normalized squared-error ∥x^−x_0∥^2_2/σ^2. Our numerical illustrations validate our theoretical predictions.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Thrampoulidis, Christos0000-0001-9053-9365
Additional Information:The work of B. Hassibi was supported in part by the National Science Foundation under grants CNS-0932428, CCF-1018927, CCF-1423663 and CCF-1409204, by the Office of Naval Research under the MURI grant N00014-08–0747, by the Jet Propulsion Lab under grant IA100076, by a grant from Qualcomm Inc., and by King Abdulaziz University.
Funding AgencyGrant Number
Office of naval Research (ONR)N00014-08–0747
King Abdulaziz UniversityUNSPECIFIED
Subject Keywords:LASSO, square-root LASSO, normalized squared error, sparse recovery, Gaussian min-max theorem
Record Number:CaltechAUTHORS:20150302-080245100
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:55386
Deposited By: Shirley Slattery
Deposited On:03 Mar 2015 02:23
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page