On the Performance of the SPICE Method

This letter considers the performance of the SPICE method in the context of line spectrum estimation by exploiting its equivalent square-root lasso (SR-LASSO) representation established in previous work. The inefficiencies of existing analyses are that the guarantees are not applicable to deterministic Fourier measurement matrices, and the studied range of the tuning parameter excludes the SR-LASSO formulation of the SPICE method. The key observation of this letter is that, for a particular range of tuning parameter, the solutions which overfit the noisy measurements are valid SR-LASSO solutions. Based on this observation, we propose to analyze these overfitting solutions and derive the condition of exact on-grid source localization that is applicable to the SPICE method. The numerical experiments demonstrate our theoretical claims.

[1]  Jian Li,et al.  New Method of Sparse Parameter Estimation in Separable Models and Its Use for Spectral Analysis of Irregularly Sampled Data , 2011, IEEE Transactions on Signal Processing.

[2]  Jian Li,et al.  SPICE: A Sparse Covariance-Based Estimation Method for Array Processing , 2011, IEEE Transactions on Signal Processing.

[3]  Wenjing Liao,et al.  MUSIC for Single-Snapshot Spectral Estimation: Stability and Super-resolution , 2014, ArXiv.

[4]  Lihua Xie,et al.  On Gridless Sparse Methods for Line Spectral Estimation From Complete and Incomplete Data , 2014, IEEE Transactions on Signal Processing.

[5]  Florentina Bunea,et al.  The Group Square-Root Lasso: Theoretical Properties and Fast Algorithms , 2013, IEEE Transactions on Information Theory.

[6]  C. Giraud.  Introduction to High-Dimensional Statistics , 2014 .

[7]  Irina Gaynanova,et al.  Oracle inequalities for high-dimensional prediction , 2016, Bernoulli.

[8]  Trevor Hastie,et al.  Statistical Learning with Sparsity: The Lasso and Generalizations , 2015 .

[9]  P. P. Vaidyanathan,et al.  Pushing the Limits of Sparse Support Recovery Using Correlation Information , 2015, IEEE Transactions on Signal Processing.

[10]  Björn E. Ottersten,et al.  Covariance Matching Estimation Techniques for Array Signal Processing Applications , 1998, Digit. Signal Process..

[11]  Håkan Hjalmarsson,et al.  A Note on the SPICE Method , 2012, IEEE Transactions on Signal Processing.

[12]  Emmanuel J. Candès,et al.  Towards a Mathematical Theory of Super‐resolution , 2012, ArXiv.

[13]  Sara A. van de Geer,et al.  Sharp Oracle Inequalities for Square Root Regularization , 2015, J. Mach. Learn. Res..

[14]  A. Derumigny.  Improved bounds for Square-Root Lasso and Square-Root Slope , 2017, 1703.02907.

[15]  S. Geer,et al.  On the conditions used to prove oracle results for the Lasso , 2009, 0910.0722.

[16]  Piya Pal,et al.  Gridless Line Spectrum Estimation and Low-Rank Toeplitz Matrix Compression Using Structured Samplers: A Regularization-Free Approach , 2017, IEEE Transactions on Signal Processing.

[17]  Gongguo Tang,et al.  Approximate support recovery of atomic line spectral estimation: A tale of resolution and precision , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[18]  Emmanuel J. Candès,et al.  Super-Resolution from Noisy Data , 2012, Journal of Fourier Analysis and Applications.

[19]  Cishen Zhang,et al.  A Discretization-Free Sparse and Parametric Approach for Linear Array Signal Processing , 2013, IEEE Transactions on Signal Processing.

[20]  Heng Qiao,et al.  A Universal Technique for Analysing Discrete Super-Resolution Algorithms , 2020, IEEE Signal Processing Letters.

[21]  S. Geer,et al.  Oracle Inequalities and Optimal Inference under Group Sparsity , 2010, 1007.1771.

[22]  Yuejie Chi,et al.  Off-the-Grid Line Spectrum Denoising and Estimation With Multiple Measurement Vectors , 2014, IEEE Transactions on Signal Processing.

[23]  Piya Pal,et al.  Guaranteed Localization of More Sources Than Sensors With Finite Snapshots in Multiple Measurement Vector Models Using Difference Co-Arrays , 2019, IEEE Transactions on Signal Processing.

[24]  Petre Stoica,et al.  Connection between SPICE and Square-Root LASSO for sparse parameter estimation , 2014, Signal Process..

[25]  Gongguo Tang,et al.  Near minimax line spectral estimation , 2013, 2013 47th Annual Conference on Information Sciences and Systems (CISS).

[26]  Wenjing Liao,et al.  Super-Resolution Limit of the ESPRIT Algorithm , 2019, IEEE Transactions on Information Theory.

[27]  Yimin Zhang,et al.  Generalized Coprime Array Configurations for Direction-of-Arrival Estimation , 2015, IEEE Transactions on Signal Processing.

[28]  Heng Qiao,et al.  On Overfitting in Discrete Super-Resolution Recovery , 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).