High-dimensional subset recovery in noise: Sparsified measurements without loss of statistical efficiency

05/20/2008
by   Dapo Omidiran, et al.
0

We consider the problem of estimating the support of a vector β^* ∈R^p based on observations contaminated by noise. A significant body of work has studied behavior of ℓ_1-relaxations when applied to measurement matrices drawn from standard dense ensembles (e.g., Gaussian, Bernoulli). In this paper, we analyze sparsified measurement ensembles, and consider the trade-off between measurement sparsity, as measured by the fraction γ of non-zero entries, and the statistical efficiency, as measured by the minimal number of observations n required for exact support recovery with probability converging to one. Our main result is to prove that it is possible to let γ→ 0 at some rate, yielding measurement matrices with a vanishing fraction of non-zeros per row while retaining the same statistical efficiency as dense ensembles. A variety of simulation results confirm the sharpness of our theoretical predictions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/04/2015

ShapeFit: Exact location recovery from corrupted pairwise directions

Let t_1,...,t_n ∈R^d and consider the location recovery problem: given a...
research
02/09/2018

Limits on Sparse Data Acquisition: RIC Analysis of Finite Gaussian Matrices

One of the key issues in the acquisition of sparse data by means of comp...
research
12/05/2013

Swapping Variables for High-Dimensional Sparse Regression with Correlated Measurements

We consider the high-dimensional sparse linear regression problem of acc...
research
03/19/2021

Refined Least Squares for Support Recovery

We study the problem of exact support recovery based on noisy observatio...
research
01/18/2019

The Restricted Isometry Property of Block Diagonal Matrices for Group-Sparse Signal Recovery

Group-sparsity is a common low-complexity signal model with widespread a...
research
10/01/2013

Jointly Clustering Rows and Columns of Binary Matrices: Algorithms and Trade-offs

In standard clustering problems, data points are represented by vectors,...
research
01/31/2023

Distribution of the number of pivots needed using Gaussian elimination with partial pivoting on random matrices

Gaussian elimination with partial pivoting (GEPP) remains the most commo...

Please sign up or login with your details

Forgot password? Click here to reset