Are good local minima wide in sparse recovery?

06/21/2018
by   Michael Moeller, et al.
0

The idea of compressed sensing is to exploit representations in suitable (overcomplete) dictionaries that allow to recover signals far beyond the Nyquist rate provided that they admit a sparse representation in the respective dictionary. The latter gives rise to the sparse recovery problem of finding the best sparse linear approximation of given data in a given generating system. In this paper we analyze the iterative hard thresholding (IHT) algorithm as one of the most popular greedy methods for solving the sparse recovery problem, and demonstrate that systematically perturbing the IHT algorithm by adding noise to intermediate iterates yields improved results. Further improvements can be obtained by entirely rephrasing the problem as a parametric deep-learning-type of optimization problem. By introducing perturbations via dropout, we demonstrate to significantly outperform the classical IHT algorithm, obtaining 3 to 6 times lower average objective errors.

READ FULL TEXT

page 3

page 4

research
09/14/2013

Optimized projections for compressed sensing via rank-constrained nearest correlation matrix

Optimizing the acquisition matrix is useful for compressed sensing of si...
research
05/07/2019

Greedy Signal Space Recovery Algorithm with Overcomplete Dictionaries in Compressive Sensing

Compressive Sensing (CS) is a new paradigm for the efficient acquisition...
research
03/17/2021

Thresholding Greedy Pursuit for Sparse Recovery Problems

We study here sparse recovery problems in the presence of additive noise...
research
06/14/2011

Orthogonal Matching Pursuit with Replacement

In this paper, we consider the problem of compressed sensing where the g...
research
11/05/2015

Sparse approximation by greedy algorithms

It is a survey on recent results in constructive sparse approximation. T...
research
10/15/2019

IRLS for Sparse Recovery Revisited: Examples of Failure and a Remedy

Compressed sensing is a central topic in signal processing with myriad a...
research
04/02/2019

Discrete Optimization Methods for Group Model Selection in Compressed Sensing

In this article we study the problem of signal recovery for group models...

Please sign up or login with your details

Forgot password? Click here to reset