{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T17:07:46Z","timestamp":1790528866650,"version":"4.1.0"},"reference-count":54,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2018,3,17]],"date-time":"2018-03-17T00:00:00Z","timestamp":1521244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Evaluating the performance of Bayesian classification in a high-dimensional random tensor is a fundamental problem, usually difficult and under-studied. In this work, we consider two Signal to Noise Ratio (SNR)-based binary classification problems of interest. Under the alternative hypothesis, i.e., for a non-zero SNR, the observed signals are either a noisy rank-R tensor admitting a Q-order Canonical Polyadic Decomposition (CPD) with large factors of size      N q  \u00d7 R    , i.e., for     1 \u2264 q \u2264 Q    , where     R ,  N q  \u2192 \u221e     with      R  1 \/ q   \/  N q      converge towards a finite constant or a noisy tensor admitting TucKer Decomposition (TKD) of multilinear     (  M 1  , \u2026 ,  M Q  )    -rank with large factors of size      N q  \u00d7  M q     , i.e., for     1 \u2264 q \u2264 Q    , where      N q  ,  M q  \u2192 \u221e     with      M q  \/  N q      converge towards a finite constant. The classification of the random entries (coefficients) of the core tensor in the CPD\/TKD is hard to study since the exact derivation of the minimal Bayes\u2019 error probability is mathematically intractable. To circumvent this difficulty, the Chernoff Upper Bound (CUB) for larger SNR and the Fisher information at low SNR are derived and studied, based on information geometry theory. The tightest CUB is reached for the value minimizing the error exponent, denoted by     s \u22c6    . In general, due to the asymmetry of the s-divergence, the Bhattacharyya Upper Bound (BUB) (that is, the Chernoff Information calculated at      s \u22c6  = 1 \/ 2    ) cannot solve this problem effectively. As a consequence, we rely on a costly numerical optimization strategy to find     s \u22c6    . However, thanks to powerful random matrix theory tools, a simple analytical expression of     s \u22c6     is provided with respect to the Signal to Noise Ratio (SNR) in the two schemes considered. This work shows that the BUB is the tightest bound at low SNRs. However, for higher SNRs, the latest property is no longer true.<\/jats:p>","DOI":"10.3390\/e20030203","type":"journal-article","created":{"date-parts":[[2018,3,20]],"date-time":"2018-03-20T06:57:11Z","timestamp":1521529031000},"page":"203","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Computational Information Geometry for Binary Classification of High-Dimensional Random Tensors"],"prefix":"10.3390","volume":"20","author":[{"given":"Gia-Thuy","family":"Pham","sequence":"first","affiliation":[{"name":"Laboratory of Signals and Systems (L2S), Department of Signals and Statistics, University of Paris-Sud, 91400 Orsay, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R\u00e9my","family":"Boyer","sequence":"additional","affiliation":[{"name":"Laboratory of Signals and Systems (L2S), Department of Signals and Statistics, University of Paris-Sud, 91400 Orsay, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5728-0726","authenticated-orcid":false,"given":"Frank","family":"Nielsen","sequence":"additional","affiliation":[{"name":"Computer Science Department LIX, \u00c9cole Polytechnique, 91120 Palaiseau, France"},{"name":"Sony Computer Science Laboratories, Tokyo 141-0022, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2018,3,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2840","DOI":"10.1109\/TSP.2006.874782","article-title":"CFAR matched direction detector","volume":"54","author":"Besson","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2400","DOI":"10.1109\/TIT.2011.2111710","article-title":"Performance of Statistical Tests for Source Detection using Random Matrix Theory","volume":"57","author":"Bianchi","year":"2011","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_3","unstructured":"Kay, S.M. (1993). Fundamentals of Statistical Signal Processing, Volume II: Detection Theory, PTR Prentice-Hall."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1934","DOI":"10.1214\/EJP.v16-943","article-title":"Almost Sure Localization of the Eigenvalues in a Gaussian Information Plus Noise Model. Application to the Spiked Models","volume":"16","author":"Loubaton","year":"2011","journal-title":"Electron. J. Probab."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5113","DOI":"10.1109\/TIT.2008.929938","article-title":"Improved Estimation of Eigenvalues and Eigenvectors of Covariance Matrices Using Their Sample Estimates","volume":"54","author":"Mestre","year":"2008","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1016\/j.jmva.2005.08.003","article-title":"Eigenvalues of large sample covariance matrices of spiked population models","volume":"97","author":"Baik","year":"2006","journal-title":"J. Multivar. Anal."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2100","DOI":"10.1109\/78.149981","article-title":"Signal detection via spectral theory of large dimensional random matrices","volume":"40","author":"Silverstein","year":"1992","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Hua, X., Wang, H., Qin, Y., and Li, X. (2016). The Geometry of Signal Detection with Applications to Radar Signal Processing. Entropy, 18.","DOI":"10.3390\/e18110381"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1111\/j.2517-6161.1966.tb00626.x","article-title":"A General Class of Coefficients of Divergence of One Distribution from Another","volume":"28","author":"Ali","year":"1966","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"ref_10","unstructured":"Cover, T.M., and Thomas, J.A. (2012). Elements of Information Theory, John Wiley & Sons."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/TCOM.1967.1089532","article-title":"The Divergence and Bhattacharyya Distance Measures in Signal Selection","volume":"15","author":"Kailath","year":"1967","journal-title":"IEEE Trans. Commun. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nielsen, F. (2013). Hypothesis Testing, Information Divergence and Computational Geometry, Springer. Geometric Science of Information.","DOI":"10.1007\/978-3-642-40020-9_25"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1326","DOI":"10.1016\/j.sigpro.2006.11.005","article-title":"Toward a theory of information processing","volume":"87","author":"Sinanovic","year":"2007","journal-title":"Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1214\/aoms\/1177729330","article-title":"A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations","volume":"23","author":"Chernoff","year":"1952","journal-title":"Ann. Math. Stat."},{"key":"ref_15","unstructured":"Nielsen, F. (arXiv, 2011). Chernoff information of exponential families, arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chepuri, S.P., and Leus, G. (2015, January 19\u201324). Sparse sensing for distributed Gaussian detection. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia.","DOI":"10.1109\/ICASSP.2015.7178400"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1109\/TIT.2009.2039039","article-title":"Performance Analysis for Sparse Support Recovery","volume":"56","author":"Tang","year":"2010","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1109\/LSP.2012.2215585","article-title":"Generalized Chernoff Information for Mismatched Bayesian Detection and Its Application to Energy Detection","volume":"19","author":"Lee","year":"2012","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3989","DOI":"10.1109\/TIT.2012.2189754","article-title":"Space-time code design for MIMO detection based on Kullback-Leibler divergence","volume":"58","author":"Grossi","year":"2012","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1902","DOI":"10.1109\/TSP.2010.2103064","article-title":"Sparsity-Based Multi-Target Tracking Using OFDM Radar","volume":"59","author":"Sen","year":"2011","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Boyer, R., and Delpha, C. (2012, January 17\u201320). Relative-entropy based beamforming for secret key transmission. Proceedings of the 2012 IEEE 7th Sensor Array and Multichannel Signal Processing Workshop (SAM), Hoboken, NJ, USA.","DOI":"10.1109\/SAM.2012.6250485"},{"key":"ref_22","unstructured":"Tran, N.D., Boyer, R., Marcos, S., and Larzabal, P. (2012, January 27\u201331). Angular resolution limit for array processing: Estimation and information theory approaches. Proceedings of the 20th European Signal Processing Conference (EUSIPCO), Bucharest, Romania."},{"key":"ref_23","unstructured":"Katz, G., Piantanida, P., Couillet, R., and Debbah, M. (October, January 30). Joint estimation and detection against independence. Proceedings of the Annual Conference on Communication Control and Computing (Allerton), Monticello, IL, USA."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1109\/LSP.2013.2243726","article-title":"An information-geometric characterization of Chernoff information","volume":"20","author":"Nielsen","year":"2013","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1109\/MSP.2013.2297439","article-title":"Tensor decompositions for signal processing applications: From two-way to multiway component analysis","volume":"32","author":"Cichocki","year":"2015","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MSP.2014.2298533","article-title":"Tensors: A brief introduction","volume":"31","author":"Comon","year":"2014","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1137\/S0895479896305696","article-title":"A Multilinear Singular Value Decomposition","volume":"21","author":"Moor","year":"2000","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF02289464","article-title":"Some mathematical notes on three-mode factor analysis","volume":"31","author":"Tucker","year":"1966","journal-title":"Psychometrika"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2997","DOI":"10.1016\/j.laa.2009.01.014","article-title":"Generic and Typical Ranks of Multi-Way Arrays","volume":"430","author":"Comon","year":"2009","journal-title":"Linear Algebra Appl."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"De Lathauwer, L. (2009, January 24\u201327). A survey of tensor methods. Proceedings of the IEEE International Symposium on Circuits and Systems, ISCAS 2009, Taipei, Taiwan.","DOI":"10.1109\/ISCAS.2009.5118377"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1002\/cem.1236","article-title":"Tensor decompositions, alternating least squares and other tales","volume":"23","author":"Comon","year":"2009","journal-title":"J. Chemom."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1109\/JSTSP.2015.2509907","article-title":"Tensor CP Decomposition with Structured Factor Matrices: Algorithms and Performance","volume":"10","author":"Goulart","year":"2016","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/BF02288367","article-title":"The approximation of one matrix by another of lower rank","volume":"1","author":"Eckart","year":"1936","journal-title":"Psychometrika"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3437","DOI":"10.1109\/TSP.2008.925924","article-title":"Fast and stable YAST algorithm for principal and minor subspace tracking","volume":"56","author":"Badeau","year":"2008","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_35","unstructured":"Boyer, R., and Badeau, R. (2006, January 14\u201319). Adaptive multilinear SVD for structured tensors. Proceedings of the 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201906), Toulouse, France."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/1687-6180-2014-119","article-title":"Low-rank filter and detector for multidimensional data based on an alternative unfolding HOSVD: Application to polarimetric STAP","volume":"2014","author":"Boizard","year":"2014","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.sigpro.2017.04.010","article-title":"Sparse-Based Estimation Performance for Partially Known Overcomplete Large-Systems","volume":"139","author":"Bouleux","year":"2017","journal-title":"Signal Process."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5525","DOI":"10.1109\/TSP.2016.2591511","article-title":"Large-System Estimation Performance in Noisy Compressed Sensing with Random Support\u2014A Bayesian Analysis","volume":"64","author":"Boyer","year":"2016","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ollier, V., Boyer, R., El Korso, M.N., and Larzabal, P. (2016, January 10\u201313). Bayesian Lower Bounds for Dense or Sparse (Outlier) Noise in the RMT Framework. Proceedings of the 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM 16), Rio de Janerio, Brazil.","DOI":"10.1109\/SAM.2016.7569694"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1093\/biomet\/20A.1-2.32","article-title":"The generalized product moment distribution in samples","volume":"20A","author":"Wishart","year":"1928","journal-title":"Biometrika"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1017\/S0305004100027237","article-title":"On the statistical distribution of the widths and spacings of nuclear resonance levels","volume":"47","author":"Wigner","year":"1951","journal-title":"Proc. Camb. Philos. Soc."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"548","DOI":"10.2307\/1970079","article-title":"Characteristic vectors of bordered matrices with infinite dimensions","volume":"62","author":"Wigner","year":"1955","journal-title":"Ann. Math."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Bai, Z.D., and Silverstein, J.W. (2010). Spectral Analysis of Large Dimensional Random Matrices, Springer. [2nd ed.].","DOI":"10.1007\/978-1-4419-0661-8"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Girko, V.L. (1990). Theory of Random Determinants, Kluwer Academic Publishers.","DOI":"10.1007\/978-94-009-1858-0"},{"key":"ref_45","first-page":"507","article-title":"Distribution of eigenvalues for some sets of random matrices","volume":"72","author":"Marchenko","year":"1967","journal-title":"Math. Sb. (N.S.)"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/BF01245072","article-title":"Limit laws for random matrices and free products","volume":"104","author":"Voiculescu","year":"1991","journal-title":"Invent. Math."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Boyer, R., and Nielsen, F. (2017, January 5\u20139). Information Geometry Metric for Random Signal Detection in Large Random Sensing Systems. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7953002"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Boyer, R., and Loubaton, P. (September, January 28). Large deviation analysis of the CPD detection problem based on random tensor theory. Proceedings of the 2017 25th European Association for Signal Processing (EUSIPCO), Kos, Greece.","DOI":"10.23919\/EUSIPCO.2017.8081289"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Lytova, A. (2017). Central Limit Theorem for Linear Eigenvalue Statistics for a Tensor Product Version of Sample Covariance Matrices. J. Theor. Prob., 1\u201334.","DOI":"10.1007\/s10959-017-0741-9"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Tulino, A.M., and Verdu, S. (2004). Random Matrix Theory and Wireless Communications, Now Publishers Inc.","DOI":"10.1561\/9781933019505"},{"key":"ref_51","unstructured":"Abramowitz, M., and Stegun, I.A. (1972). \u201cElliptic Integrals\u201d (Chapter 17). Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables, Dover Publications. [9th printing]."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1109\/78.286957","article-title":"Signal processing applications of oblique projection operators","volume":"42","author":"Behrens","year":"1994","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"11","DOI":"10.4064\/sm195-1-2","article-title":"On the Limiting Empirical Measure of the sum of rank one matrices with log-concave distribution","volume":"195","author":"Pajor","year":"2009","journal-title":"Stud. Math."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s00220-011-1411-x","article-title":"Random matrix theory: Extending random matrix theory to mixtures of random product states","volume":"310","author":"Ambainis","year":"2012","journal-title":"Commun. Math. Phys."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/20\/3\/203\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:57:27Z","timestamp":1760194647000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/20\/3\/203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,17]]},"references-count":54,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,3]]}},"alternative-id":["e20030203"],"URL":"https:\/\/doi.org\/10.3390\/e20030203","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3,17]]}}}