On the Error in Phase Transition Computations for Compressed Sensing

06/27/2018
by   Sajad Daei, et al.
0

Evaluating the statistical dimension is a common tool to determine the asymptotic phase transition in compressed sensing problems with Gaussian ensemble. Unfortunately, the exact evaluation of the statistical dimension is very difficult and it has become standard to replace it with an upper-bound. To ensure that this technique is suitable, [1] has introduced an upper-bound on the gap between the statistical dimension and its approximation. In this work, we first show that the error bound in [1] in some low-dimensional models such as total variation and ℓ_1 analysis minimization becomes poorly large. Next, we develop a new error bound which significantly improves the estimation gap compared to [1]. In particular, unlike the bound in [1] that is not applicable to settings with overcomplete dictionaries, our bound exhibits a decaying behavior in such cases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/08/2018

Sample Complexity of Total Variation Minimization

This work considers the use of Total variation (TV) minimization in the ...
research
10/11/2012

Near-optimal compressed sensing guarantees for total variation minimization

Consider the problem of reconstructing a multidimensional signal from an...
research
07/17/2013

Universally Elevating the Phase Transition Performance of Compressed Sensing: Non-Isometric Matrices are Not Necessarily Bad Matrices

In compressed sensing problems, ℓ_1 minimization or Basis Pursuit was kn...
research
09/15/2015

Precise Phase Transition of Total Variation Minimization

Characterizing the phase transitions of convex optimizations in recoveri...
research
01/30/2011

Statistical Compressed Sensing of Gaussian Mixture Models

A novel framework of compressed sensing, namely statistical compressed s...
research
09/08/2019

Living near the edge: A lower-bound on the phase transition of total variation minimization

This work is about the total variation (TV) minimization which is used f...
research
07/27/2022

Exact spectral norm error of sample covariance

Let X_1,…,X_n be i.i.d. centered Gaussian vectors in ℝ^p with covariance...

Please sign up or login with your details

Forgot password? Click here to reset