Paper Info
Title
Threshold effects in parameter estimation from compressed data
Abstract
In this paper, we investigate threshold effects associated with swapping of signal and noise subspaces in estimating signal parameters from compressed noisy data. The term threshold effect refers to a catastrophic increase in mean-squared error when the signal-to-noise ratio falls below a threshold SNR. In many cases, the threshold effect is caused by a subspace swap event, when the measured data (or its sample covariance) is better approximated by a subset of components of an orthogonal subspace than by the components of a signal subspace. We derive analytical lower bounds on the probability of the subspace swap in compressively measured noisy data. These bounds guide our understanding of threshold effects and performance breakdown for parameter estimation using compression. As a case study, we investigate threshold effects in MUSIC estimation of direction of arrivals of two closely-spaced sources using Gaussian random compression and co-prime subsampling. Our results show the impact of compression on threshold SNR.
Year
DOI
Venue
2013
10.1109/GlobalSIP.2013.6737061
GlobalSIP
Keywords
DocType
ISSN
music estimation,gaussian random compression,subspace swap event,cramer-rao bound,signal sampling,parameter estimation,performance breakdown,analytical lower bounds,signal parameters,direction of arrivals,co-prime sampling,threshold effects,data compression,mean-squared error,orthogonal subspace,mean squared error,compressed data,subspace swap,music algorithm,closely-spaced sources,random compression,noise subspaces,gaussian processes,threshold snr,coprime subsampling,measured noisy data,signal subspace,signal-to-noise ratio,probability,compressed noisy data
Conference
2376-4066
Citations 
PageRank 
References 
2
0.41
0
Authors
3
Name
Order
Citations
PageRank
Pooria Pakrooh1445.24
Ali Pezeshki245038.31
Louis L. Scharf32525414.45