Compressed sensing (CS) involves sampling signals at rates less than their Nyquist rates and attempting to reconstruct them after sample acquisition. Most such algorithms have parameters, for example the regularization parameter in LASSO, which need to be chosen carefully for optimal performance. These parameters can be chosen based on assumptions on the noise level or signal sparsity, but this knowledge may often be unavailable. In such cases, cross validation (CV) can be used to choose these parameters in a purely data-driven fashion. Previous work analyzing the use of CV in CS has been based on the $\ell_{2}$ cross-validation error with Gaussian measurement noise. But it is well known that the $\ell_{2}$ error is not robust to impulse noise and provides a poor estimate of the recovery error, failing to choose the best parameter. Here we propose using the $\ell_{1}-\mathbf{CV}$ error which provides substantial performance benefits given impulse measurement noise. Most importantly, we provide a detailed theoretical analysis and error bounds for the use of $\ell_{1}-\mathbf{CV}$ error in CS reconstruction. We show that with high probability, choosing the parameter that yields the minimum $\ell_{1}-\mathbf{CV}$ error is equivalent to choosing the minimum recovery error (which is not observable in practice). To our best knowledge, this is the first paper which theoretically analyzes $\ell_{1}$ -based CV in CS.
[1]
George Tzagkarakis,et al.
Compressive Sensing Using Symmetric Alpha-Stable Distributions for Robust Sparse Signal Reconstruction
,
2019,
IEEE Transactions on Signal Processing.
[2]
Trevor Hastie,et al.
Statistical Learning with Sparsity: The Lasso and Generalizations
,
2015
.
[3]
Rachel Ward,et al.
Compressed Sensing With Cross Validation
,
2008,
IEEE Transactions on Information Theory.
[4]
Yuantao Gu,et al.
On the theoretical analysis of cross validation in compressive sensing
,
2014,
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[5]
Joel A. Tropp,et al.
Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit
,
2007,
IEEE Transactions on Information Theory.
[6]
Brian M. Sadler,et al.
Robust compressive sensing of sparse signals: a review
,
2016,
EURASIP J. Adv. Signal Process..
[7]
Richard G. Baraniuk,et al.
Sparse Signal Reconstruction from Noisy Compressive Measurements using Cross Validation
,
2007,
2007 IEEE/SP 14th Workshop on Statistical Signal Processing.