Cross-Validated Tuning of Shrinkage Factors for MVDR Beamforming Based on Regularized Covariance Matrix Estimation

This paper considers the regularized estimation of covariance matrices (CM) of high-dimensional (compound) Gaussian data for minimum variance distortionless response (MVDR) beamforming. Linear shrinkage is applied to improve the accuracy and condition number of the CM estimate for lowsample-support cases. We focus on data-driven techniques that automatically choose the linear shrinkage factors for shrinkage sample covariance matrix (SCM) and shrinkage Tyler’s estimator (STE) by exploiting cross validation (CV). We propose leaveone-out cross-validation (LOOCV) choices for the shrinkage factors to optimize the beamforming performance, referred to as SCM-CV and STE-CV. The (weighted) out-of-sample output power of the beamfomer is chosen as a proxy of the beamformer performance and concise expressions of the LOOCV cost function are derived to allow fast optimization. For the large system regime, asymptotic approximations of the LOOCV cost functions are derived, yielding the SCM-AE and STE-AE. In general, the proposed algorithms are able to achieve near-oracle performance in choosing the linear shrinkage factors for MVDR beamforming. Simulation results are provided for validating the proposed methods.

[1]  C. Baker.  K-distributed coherent sea clutter , 1991 .

[2]  Jiangtao Xi,et al.  Regularized Estimation of Kronecker-Structured Covariance Matrix , 2021 .

[3]  Jiangtao Xi,et al.  Linear shrinkage estimation of covariance matrices using low-complexity cross-validation , 2018, Signal Process..

[4]  Matthew R. McKay,et al.  High-Dimensional MVDR Beamforming: Optimized Solutions Based on Spiked Random Matrix Models , 2018, IEEE Transactions on Signal Processing.

[5]  Xiaoming Chen,et al.  A simple tridiagonal loading method for robust adaptive beamforming , 2019, Signal Process..

[6]  Antonio De Maio,et al.  Censoring Outliers in Radar Data: An Approximate ML Approach and its Analysis , 2019, IEEE Transactions on Aerospace and Electronic Systems.

[7]  Olivier Besson,et al.  Performance analysis of beamformers using generalized loading of the covariance matrix in the presence of random steering vector errors , 2005, IEEE Transactions on Signal Processing.

[8]  E. J. Kelly.  An Adaptive Detection Algorithm , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[9]  Jian Li,et al.  Fully automatic computation of diagonal loading levels for robust adaptive beamforming , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  J.R. Guerci,et al.  Knowledge-aided adaptive radar at DARPA: an overview , 2006, IEEE Signal Processing Magazine.

[11]  Philippe Forster,et al.  Asymptotic Properties of Robust Complex Covariance Matrix Estimates , 2012, IEEE Transactions on Signal Processing.

[12]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .

[13]  B. Carlson.  Covariance matrix estimation errors and diagonal loading in adaptive arrays , 1988 .

[14]  K. J. Sangston,et al.  Structures for radar detection in compound Gaussian clutter , 1999 .

[15]  Olivier Besson,et al.  On the Expected Likelihood Approach for Assessment of Regularization Covariance Matrix , 2015, IEEE Signal Processing Letters.

[16]  J. Capon.  High-resolution frequency-wavenumber spectrum analysis , 1969 .

[17]  Fulvio Gini,et al.  Cramér-Rao Lower Bounds on Covariance Matrix Estimation for Complex Elliptically Symmetric Distributions , 2013, IEEE Transactions on Signal Processing.

[18]  Mohamed-Slim Alouini,et al.  Optimal Design of the Adaptive Normalized Matched Filter Detector Using Regularized Tyler Estimators , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[19]  Alfred O. Hero,et al.  Shrinkage Algorithms for MMSE Covariance Estimation , 2009, IEEE Transactions on Signal Processing.

[20]  Philippe Forster,et al.  Covariance Structure Maximum-Likelihood Estimates in Compound Gaussian Noise: Existence and Algorithm Analysis , 2008, IEEE Transactions on Signal Processing.

[21]  Matthew R. McKay,et al.  Large-Dimensional Behavior of Regularized Maronna's M-Estimators of Covariance Matrices , 2018, IEEE Transactions on Signal Processing.

[22]  Vishal Monga,et al.  Rank-Constrained Maximum Likelihood Estimation of Structured Covariance Matrices , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[23]  Esa Ollila,et al.  Shrinking the Eigenvalues of M-Estimators of Covariance Matrix , 2021, IEEE Transactions on Signal Processing.

[24]  Mayer Aladjem,et al.  Multi-Target Shrinkage Estimation for Covariance Matrices , 2014, IEEE Transactions on Signal Processing.

[25]  Kung Yao,et al.  A representation theorem and its applications to spherically-invariant random processes , 1973, IEEE Trans. Inf. Theory.

[26]  Samruddhi Deshmukh,et al.  Improved Covariance Matrix Estimation With an Application in Portfolio Optimization , 2020, IEEE Signal Processing Letters.

[27]  H. Vincent Poor,et al.  Complex Elliptically Symmetric Distributions: Survey, New Results and Applications , 2012, IEEE Transactions on Signal Processing.

[28]  Romain Couillet,et al.  Robust Estimates of Covariance Matrices in the Large Dimensional Regime , 2012, IEEE Transactions on Information Theory.

[29]  O. Besson,et al.  Steering vector errors and diagonal loading , 2004 .

[30]  Jian Li,et al.  On Using a priori Knowledge in Space-Time Adaptive Processing , 2008, IEEE Transactions on Signal Processing.

[31]  Xiang Li,et al.  GLRT detector based on knowledge aided covariance estimation in compound Gaussian environment , 2019, Signal Process..

[32]  R. Maronna.  Robust $M$-Estimators of Multivariate Location and Scatter , 1976 .

[33]  Mohamed-Slim Alouini,et al.  Fluctuations of the SNR at the output of the MVDR with regularized Tyler estimators , 2016, Signal Process..

[34]  Ning Ma,et al.  Efficient method to determine diagonal loading value , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[35]  David E. Tyler.  A Distribution-Free $M$-Estimator of Multivariate Scatter , 1987 .

[36]  F. Hampel.  The Influence Curve and Its Role in Robust Estimation , 1974 .

[37]  J. W. Silverstein,et al.  No eigenvalues outside the support of the limiting spectral distribution of large-dimensional sample covariance matrices , 1998 .

[38]  Antonia Maria Tulino,et al.  Random Matrix Theory and Wireless Communications , 2004, Found. Trends Commun. Inf. Theory.

[39]  L. Godara.  Application of antenna arrays to mobile communications. II. Beam-forming and direction-of-arrival considerations , 1997, Proc. IEEE.

[40]  James Ward,et al.  Space-time adaptive processing for airborne radar , 1994, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[41]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[42]  Dallan Byrne,et al.  Time-Domain Wideband Adaptive Beamforming for Radar Breast Imaging , 2015, IEEE Transactions on Antennas and Propagation.

[43]  Karl Gerlach,et al.  Fast converging adaptive processor or a structured covariance matrix , 2000, IEEE Trans. Aerosp. Electron. Syst..

[44]  E. Conte,et al.  Characterization of radar clutter as a spherically invariant random process , 1987 .

[45]  J. Bouchaud,et al.  Financial Applications of Random Matrix Theory: a short review , 2009, 0910.1205.

[46]  Matthew R. McKay,et al.  Large dimensional analysis and optimization of robust shrinkage covariance matrix estimators , 2014, J. Multivar. Anal..

[47]  I. Reed,et al.  Rapid Convergence Rate in Adaptive Arrays , 1974, IEEE Transactions on Aerospace and Electronic Systems.

[48]  Jiangtao Xi,et al.  Shrinkage of Covariance Matrices for Linear Signal Estimation Using Cross-Validation , 2016, IEEE Transactions on Signal Processing.

[49]  W.L. Melvin,et al.  A STAP overview , 2004, IEEE Aerospace and Electronic Systems Magazine.

[50]  Lingjiang Kong,et al.  Geometric barycenters for covariance estimation in compound‐Gaussian clutter , 2017 .

[51]  P. Bickel,et al.  Regularized estimation of large covariance matrices , 2008, 0803.1909.

[52]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[53]  Jian Li,et al.  On robust Capon beamforming and diagonal loading , 2003, IEEE Trans. Signal Process..

[54]  Augusto Aubry,et al.  Median matrices and their application to radar training data selection , 2014 .

[55]  J. Guerci,et al.  Improved clutter mitigation performance using knowledge-aided space-time adaptive processing , 2006, IEEE Transactions on Aerospace and Electronic Systems.

[56]  Xavier Mestre,et al.  Finite sample size effect on minimum variance beamformers: optimum diagonal loading factor for large arrays , 2006, IEEE Transactions on Signal Processing.

[57]  Esa Ollila,et al.  Optimal Shrinkage Covariance Matrix Estimation Under Random Sampling From Elliptical Distributions , 2018, IEEE Transactions on Signal Processing.

[58]  Augusto Aubry,et al.  A Geometric Approach to Covariance Matrix Estimation and its Applications to Radar Problems , 2017, IEEE Transactions on Signal Processing.

[59]  Esa Ollila,et al.  Regularized $M$ -Estimators of Scatter Matrix , 2014, IEEE Transactions on Signal Processing.

[60]  Alfred O. Hero,et al.  Robust Shrinkage Estimation of High-Dimensional Covariance Matrices , 2010, IEEE Transactions on Signal Processing.

[61]  Zhi-Quan Luo,et al.  Robust adaptive beamforming using worst-case performance optimization: a solution to the signal mismatch problem , 2003, IEEE Trans. Signal Process..

[62]  Jean-Philippe Bouchaud,et al.  Cleaning large correlation matrices: tools from random matrix theory , 2016, 1610.08104.

[63]  Augusto Aubry,et al.  Maximum Likelihood Estimation of a Structured Covariance Matrix With a Condition Number Constraint , 2012, IEEE Transactions on Signal Processing.

[64]  Wei Zhang,et al.  A Recursive Angle-Doppler Channel Selection Method for Reduced-Dimension Space-Time Adaptive Processing , 2020, IEEE Transactions on Aerospace and Electronic Systems.

[65]  Jiangtao Xi,et al.  Tuning the Parameters for Precision Matrix Estimation Using Regression Analysis , 2019, IEEE Access.

[66]  Fulvio Gini,et al.  Statistical analyses of measured radar ground clutter data , 1999 .

[67]  K. Strimmer,et al.  Statistical Applications in Genetics and Molecular Biology A Shrinkage Approach to Large-Scale Covariance Matrix Estimation and Implications for Functional Genomics , 2011 .

[68]  L.E. Brennan,et al.  Theory of Adaptive Radar , 1973, IEEE Transactions on Aerospace and Electronic Systems.

[69]  Olivier Besson,et al.  Regularized Covariance Matrix Estimation in Complex Elliptically Symmetric Distributions Using the Expected Likelihood Approach— Part 1: The Over-Sampled Case , 2013, IEEE Transactions on Signal Processing.

[70]  Leslie M. Novak,et al.  Optimal polarimetric processing for enhanced target detection , 1993 .

[71]  Emanuel A. P. Habets,et al.  New Insights Into the MVDR Beamformer in Room Acoustics , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[72]  David A. Landgrebe,et al.  Covariance Matrix Estimation and Classification With Limited Training Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[73]  Prabhu Babu,et al.  Regularized Tyler's Scatter Estimator: Existence, Uniqueness, and Algorithms , 2014, IEEE Transactions on Signal Processing.

[74]  Jiangtao Xi,et al.  Low-complexity cross-validation design of a linear estimator , 2017 .

[75]  Daniel R. Fuhrmann,et al.  A CFAR adaptive matched filter detector , 1992 .