Modal clustering of matrix-variate data. (English) Zbl 07702484
Summary: The nonparametric formulation of density-based clustering, known as modal clustering, draws a correspondence between groups and the attraction domains of the modes of the density function underlying the data. Its probabilistic foundation allows for a natural, yet not trivial, generalization of the approach to the matrix-valued setting, increasingly widespread, for example, in longitudinal and multivariate spatio-temporal studies. In this work we introduce nonparametric estimators of matrix-variate distributions based on kernel methods, and analyze their asymptotic properties. Additionally, we propose a generalization of the mean-shift procedure for the identification of the modes of the estimated density. Given the intrinsic high dimensionality of matrix-variate data, we discuss some locally adaptive solutions to handle the problem. We test the procedure via extensive simulations, also with respect to some competitors, and illustrate its performance through two high-dimensional real data applications.
MSC:
| 62G05 | Nonparametric estimation |
| 62H30 | Classification and discrimination; cluster analysis (statistical aspects) |
References:
| [1] | Altun K, Barshan B (2010) Human activity recognition using inertial/magnetic sensor units. In: International workshop on human behavior understanding. Springer, Berlin, pp 38-51 |
| [2] | Altun, K.; Barshan, B.; Tunçel, O., Comparative study on classifying human activities with miniature inertial and magnetic sensors, Pattern Recogn, 43, 10, 3605-3620 (2010) · Zbl 1213.68513 · doi:10.1016/j.patcog.2010.04.019 |
| [3] | Arias-Castro, E.; Mason, D.; Pelletier, B., On the estimation of the gradient lines of a density and the consistency of the mean-shift algorithm, J Mach Learn Res, 17, 1, 1487-1514 (2016) · Zbl 1360.62150 |
| [4] | Barshan, B.; Yüksek, MC, Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units, Comput J, 57, 11, 1649-1667 (2014) · doi:10.1093/comjnl/bxt075 |
| [5] | Basford, KE; McLachlan, GJ, The mixture method of clustering applied to three-way data, J Classif, 2, 1, 109-125 (1985) · doi:10.1007/BF01908066 |
| [6] | Caro-Lopera, FJ; Farías, GG; Balakrishnan, N., Matrix-variate distribution theory under elliptical models-4: joint distribution of latent roots of covariance matrix and the largest and smallest latent roots, J Multivar Anal, 145, 224-235 (2016) · Zbl 1333.62143 · doi:10.1016/j.jmva.2015.12.012 |
| [7] | Chacón, JE, A population background for nonparametric density-based clustering, Stat Sci, 30, 4, 518-532 (2015) · Zbl 1426.62181 · doi:10.1214/15-STS526 |
| [8] | Chacón, JE; Duong, T., Multivariate kernel smoothing and its applications (2018), Cambridge: CRC Press, Cambridge · Zbl 1402.62003 · doi:10.1201/9780429485572 |
| [9] | Chakraborty, R.; Vemuri, BC, Statistics on the Stiefel manifold: theory and applications, Ann Stat, 47, 1, 415-438 (2019) · Zbl 1419.62132 · doi:10.1214/18-AOS1692 |
| [10] | Diggle, P.; Diggle, PJ; Heagerty, P.; Liang, K-Y; Heagerty, PJ; Zeger, S., Analysis of longitudinal data (2002), Oxford: Oxford University Press, Oxford |
| [11] | Ding, S.; Cook, DR, Matrix variate regressions and envelope models, J R Stat Soc Ser B (Stat Methodol), 80, 2, 387-408 (2018) · Zbl 06849260 · doi:10.1111/rssb.12247 |
| [12] | Dryden, IL; Koloydenko, A.; Zhou, D., Non-euclidean statistics for covariance matrices, with applications to diffusion tensor imaging, Ann Appl Stat, 3, 3, 1102-1123 (2009) · Zbl 1196.62063 · doi:10.1214/09-AOAS249 |
| [13] | Duong T (2019) ks: Kernel Smoothing. R package version 1.11.5. https://CRAN.R-project.org/package=ks |
| [14] | Duong, T.; Cowling, A.; Koch, I.; Wand, MP, Feature significance for multivariate kernel density estimation, Comput Stat Data Anal, 52, 9, 4225-4242 (2008) · Zbl 1452.62265 · doi:10.1016/j.csda.2008.02.035 |
| [15] | Duong, T.; Beck, G.; Azzag, H.; Lebbah, M., Nearest neighbour estimators of density derivatives, with application to mean shift clustering, Pattern Recogn Lett, 80, 224-230 (2016) · doi:10.1016/j.patrec.2016.06.021 |
| [16] | Ferraccioli, F.; Menardi, G.; Porzio, G.; Rampichini, C.; Bocci, C., A nonparametric test for mode significance, Cladag, 2021, Book of abstracts and short papers, 388-391 (2021), New York: Firenze University Press, New York |
| [17] | Fukunaga, K.; Hostetler, L., The estimation of the gradient of a density function, with applications in pattern recognition, IEEE Trans Inf Theory, 21, 1, 32-40 (1975) · Zbl 0297.62025 · doi:10.1109/TIT.1975.1055330 |
| [18] | Gallaugher, MP; McNicholas, PD, Finite mixtures of skewed matrix variate distributions, Pattern Recogn, 80, 83-93 (2018) · doi:10.1016/j.patcog.2018.02.025 |
| [19] | Genovese, CR; Perone-Pacifico, M.; Verdinelli, I.; Wasserman, L., Non-parametric inference for density modes, J R Stat Soc B, 78, 99-126 (2016) · Zbl 1411.62093 · doi:10.1111/rssb.12111 |
| [20] | Ghassabeh, YA, A sufficient condition for the convergence of the mean shift algorithm with gaussian kernel, J Multivar Anal, 135, 1-10 (2015) · Zbl 1308.62118 · doi:10.1016/j.jmva.2014.11.009 |
| [21] | Gupta, AK; Nagar, DK, Matrix variate distributions (2018), Cambridge: CRC Press, Cambridge · Zbl 0935.62064 · doi:10.1201/9780203749289 |
| [22] | Hale T, Webster S, Petherick A, Phillips T, Kira B (2020) Oxford covid-19 government response tracker |
| [23] | Hennig, C.; Meila, M.; Murtagh, F.; Rocci, R., Handbook of cluster analysis (2015), Cambridge: CRC Press, Cambridge · doi:10.1201/b19706 |
| [24] | Jacques, J.; Preda, C., Model-based clustering for multivariate functional data, Comput Stat Data Anal, 71, 92-106 (2014) · Zbl 1471.62096 · doi:10.1016/j.csda.2012.12.004 |
| [25] | Kroonenberg, PM, Applied multiway data analysis (2008), New York: Wiley, New York · Zbl 1160.62002 · doi:10.1002/9780470238004 |
| [26] | Makhoul, J., A fast cosine transform in one and two dimensions, IEEE Trans Acoust Speech Signal Process, 28, 1, 27-34 (1980) · Zbl 0522.65092 · doi:10.1109/TASSP.1980.1163351 |
| [27] | Menardi, G., A review on modal clustering, Int Stat Rev, 84, 3, 413-433 (2016) · Zbl 07763532 · doi:10.1111/insr.12109 |
| [28] | R Core Team (2020) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. https://www.R-project.org/ |
| [29] | Rousseeuw, PJ, Silhouettes: a graphical aid to the interpretation and validation of cluster analysis, J Comput Appl Math, 20, 53-65 (1987) · Zbl 0636.62059 · doi:10.1016/0377-0427(87)90125-7 |
| [30] | Sakata, T., Applied matrix and tensor variate data analysis (2016), Berlin: Springer, Berlin · Zbl 1333.62005 · doi:10.1007/978-4-431-55387-8 |
| [31] | Sarkar, S.; Zhu, X.; Melnykov, V.; Ingrassia, S., On parsimonious models for modeling matrix data, Comput Stat Data Anal, 142, 106822 (2020) · Zbl 1507.62152 · doi:10.1016/j.csda.2019.106822 |
| [32] | Schmutz A, Jacques J, Bouveyron C, Cheze L, Martin P (2020) Clustering multivariate functional data in group-specific functional subspaces. Comput Stat 1-31 |
| [33] | Strang, G., The discrete cosine transform, SIAM Rev, 41, 1, 135-147 (1999) · Zbl 0939.42021 · doi:10.1137/S0036144598336745 |
| [34] | Stuetzle, W., Estimating the cluster tree of a density by analyzing the minimal spanning tree of a sample, J Classif, 20, 1, 25-47 (2003) · Zbl 1055.62075 · doi:10.1007/s00357-003-0004-6 |
| [35] | Tomarchio, SD; Punzo, A.; Bagnato, L., Two new matrix-variate distributions with application in model-based clustering, Comput Stat Data Anal, 152, 107050 (2020) · Zbl 1510.62235 · doi:10.1016/j.csda.2020.107050 |
| [36] | Vermunt, JK, A hierarchical mixture model for clustering three-way data sets, Comput Stat Data Anal, 51, 11, 5368-5376 (2007) · Zbl 1445.62154 · doi:10.1016/j.csda.2006.08.005 |
| [37] | Vichi, M.; Rocci, R.; Kiers, HA, Simultaneous component and clustering models for three-way data: within and between approaches, J Classif, 24, 1, 71-98 (2007) · Zbl 1144.62045 · doi:10.1007/s00357-007-0006-x |
| [38] | Viroli, C., Finite mixtures of matrix normal distributions for classifying three-way data, Stat Comput, 21, 4, 511-522 (2011) · Zbl 1221.62083 · doi:10.1007/s11222-010-9188-x |
| [39] | Viroli, C., On matrix-variate regression analysis, J Multivar Anal, 111, 296-309 (2012) · Zbl 1259.62060 · doi:10.1016/j.jmva.2012.04.005 |
| [40] | Viroli, C., Model based clustering for three-way data structures, Bayesian Anal, 6, 4, 573-602 (2011) · Zbl 1330.62262 · doi:10.1214/11-BA622 |
| [41] | Wang, M.; Fischer, J.; Song, YS, Three-way clustering of multi-tissue multi-individual gene expression data using semi-nonnegative tensor decomposition, Annals Appl Stat, 13, 2, 1103-1127 (2019) · Zbl 1423.62152 · doi:10.1214/18-AOAS1228 |
| [42] | Zhou, H.; Li, L., Regularized matrix regression, J R Stat Soc Ser B (Stat Methodol), 76, 2, 463-483 (2014) · Zbl 07555458 · doi:10.1111/rssb.12031 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
