Geodesic
Limiting spectral distribution for large sample covariance matrices with graph-dependent elements
Teoriâ veroâtnostej i ee primeneniâ, Tome 67 (2022) no. 3, pp. 471-488 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

For sample covariance matrices associated with random vectors having graph dependent entries and a number of dimensions growing with the sample size, we derive sharp conditions for the limiting spectrum of the matrices to have the same form as in the case of Gaussian data with similar covariance structure. Our results are tight. In particular, they give necessary and sufficient conditions for the Marchenko–Pastur theorem for sample covariance matrices associated with random vectors having $m$-dependent orthonormal elements when $m=o(n)$.
Mots-clés : random matrices, covariance matrices
Keywords: the Marchenko–Pastur law. 
@article{TVP_2022_67_3_a3,
     author = {P. A. Yaskov},
     title = {Limiting spectral distribution for large sample covariance matrices with graph-dependent elements},
     journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
     pages = {471--488},
     year = {2022},
     volume = {67},
     number = {3},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/TVP_2022_67_3_a3/}
}
TY  - JOUR
AU  - P. A. Yaskov
TI  - Limiting spectral distribution for large sample covariance matrices with graph-dependent elements
JO  - Teoriâ veroâtnostej i ee primeneniâ
PY  - 2022
SP  - 471
EP  - 488
VL  - 67
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/TVP_2022_67_3_a3/
LA  - ru
ID  - TVP_2022_67_3_a3
ER  - 
%0 Journal Article
%A P. A. Yaskov
%T Limiting spectral distribution for large sample covariance matrices with graph-dependent elements
%J Teoriâ veroâtnostej i ee primeneniâ
%D 2022
%P 471-488
%V 67
%N 3
%U http://geodesic.mathdoc.fr/item/TVP_2022_67_3_a3/
%G ru
%F TVP_2022_67_3_a3
P. A. Yaskov. Limiting spectral distribution for large sample covariance matrices with graph-dependent elements. Teoriâ veroâtnostej i ee primeneniâ, Tome 67 (2022) no. 3, pp. 471-488. http://geodesic.mathdoc.fr/item/TVP_2022_67_3_a3/

[1] R. Adamczak, “On the Marchenko–Pastur and circular laws for some classes of random matrices with dependent entries”, Electron. J. Probab., 16:37 (2011), 1065–1095 | DOI | MR | Zbl

[2] Zhidong Bai, Wang Zhou, “Large sample covariance matrices without independence structures in columns”, Statist. Sinica, 18:2 (2008), 425–442 | MR | Zbl

[3] Zhidong Bai, J. W. Silverstein, Spectral analysis of large dimensional random matrices, Springer Ser. Statist., 2nd ed., Springer, New York, 2010, xvi+551 pp. | DOI | MR | Zbl

[4] M. Banna, F. Merlevéde, M. Peligrad, “On the limiting spectral distribution for a large class of symmetric random matrices with correlated entries”, Stochastic Process. Appl., 125:7 (2015), 2700–2726 | DOI | MR | Zbl

[5] V. I. Bogachev, Measure theory, v. I, Springer-Verlag, Berlin, 2007, xviii+500 pp. | DOI | MR | Zbl

[6] J. Bun, J.-P. Bouchaud, M. Potters, “Cleaning large correlation matrices: tools from random matrix theory”, Phys. Rep., 666 (2017), 1–109 | DOI | MR | Zbl

[7] J. Bryson, R. Vershynin, Hongkai Zhao, “Marchenko–Pastur law with relaxed independence conditions”, Random Matrices Theory Appl., 10:4 (2021), 2150040, 28 pp. | DOI | MR

[8] V. L. Girko, A. K. Gupta, “Asymptotic behavior of spectral function of empirical covariance matrices”, Random Oper. Stochastic Equations, 2:1 (1994), 43–60 | DOI | MR | Zbl

[9] E. Dobriban, S. Wager, “High-dimensional asymptotics of prediction: ridge regression and classification”, Ann. Statist., 46:1 (2018), 247–279 | DOI | MR | Zbl

[10] F. Götze, A. A. Naumov, A. N. Tikhomirov, “Limit theorems for two classes of random matrices with dependent entries”, Theory Probab. Appl., 59:1 (2015), 23–39 | DOI | DOI | MR | Zbl

[11] P. Hall, “On the $L^p$ convergence of sums of independent random variables”, Math. Proc. Cambridge Philos. Soc., 82:3 (1977), 439–446 | DOI | MR | Zbl

[12] Jun Hui, Guangming Pan, “Limiting spectral distribution for large sample covariance matrices with $m$-dependent elements”, Comm. Statist. Theory Methods, 39:6 (2010), 935–941 | DOI | MR | Zbl

[13] S. Janson, “Large deviations for sums of partly dependent random variables”, Random Structures Algorithms, 24:3 (2004), 234–248 | DOI | MR | Zbl

[14] N. El Karoui, “Random matrices and high-dimensional statistics: beyond covariance matrices”, Proceedings of the international congress of mathematicians (ICM 2018) (Rio de Janeiro, 2018), v. 4, World Sci. Publ., Hackensack, NJ, 2018, 2857–2876 | DOI | MR | Zbl

[15] N. El Karoui, “Concentration of measure and spectra of random matrices: applications to correlation matrices, elliptical distributions and beyond”, Ann. Appl. Probab., 19:6 (2009), 2362–2405 | DOI | MR | Zbl

[16] A. Lytova, “Central limit theorem for linear eigenvalue statistics for a tensor product version of sample covariance matrices”, J. Theoret. Probab., 31:2 (2018), 1024–1057 | DOI | MR | Zbl

[17] J. R. Magnus, “The moments of products of quadratic forms in normal variables”, Statist. Neerlandica, 32:4 (1978), 201–210 | DOI | MR | Zbl

[18] V. A. Marčenko, L. A. Pastur, “Distribution of eigenvalues for some sets of random matrices”, Math. USSR-Sb., 1:4 (1967), 457–483 | DOI | MR | Zbl

[19] F. Merlevède, M. Peligrad, “On the empirical spectral distribution for matrices with long memory and independent rows”, Stochastic Process. Appl., 126:9 (2016), 2734–2760 | DOI | MR | Zbl

[20] F. Merlevede, C. Peligrad, M. Peligrad, “On the universality of spectral limit for random matrices with martingale differences entries”, Random Matrices Theory Appl., 4:1 (2015), 1550003, 33 pp. | DOI | MR | Zbl

[21] S. O'Rourke, “A note on the Marchenko–Pastur law for a class of random matrices with dependent entries”, Electron. Commun. Probab., 17 (2012), 28, 13 pp. | DOI | MR | Zbl

[22] A. Pajor, L. Pastur, “On the limiting empirical measure of eigenvalues of the sum of rank one matrices with log-concave distribution”, Studia Math., 195:1 (2009), 11–29 | DOI | MR | Zbl

[23] L. Pastur, M. Shcherbina, Eigenvalue distribution of large random matrices, Math. Surveys Monogr., 171, Amer. Math. Soc., Providence, RI, 2011, xiv+632 pp. | DOI | MR | Zbl

[24] V. V. Petrov, Limit theorems of probability theory. Sequences of independent random variables, Oxford Stud. Probab., 4, The Clarendon Press, Oxford Univ. Press, New York, 1995, xii+292 pp. | MR | Zbl

[25] Meng Wei, Guangyu Yang, Lingling Ying, “The limiting spectral distribution for large sample covariance matrices with unbounded $m$-dependent entries”, Comm. Statist. Theory Methods, 45:22 (2016), 6651–6662 | DOI | MR | Zbl

[26] Jianfeng Yao, “A note on a Marčenko–Pastur type theorem for time series”, Statist. Probab. Lett., 82:1 (2012), 22–28 | DOI | MR | Zbl

[27] P. Yaskov, The universality principle for spectral distributions of sample covariance matrices, 2014, 71 pp., arXiv: 1410.5190

[28] P. Yaskov, “Variance inequalities for quadratic forms with applications”, Math. Methods Statist., 24:4 (2015), 309–319 | DOI | MR | Zbl

[29] P. Yaskov, “Necessary and sufficient conditions for the Marchenko–Pastur theorem”, Electron. Commun. Probab., 21 (2016), 73, 8 pp. | DOI | MR | Zbl

[30] P. Yaskov, “LLN for quadratic forms of long memory time series and its applications in random matrix theory”, J. Theoret. Probab., 31:4 (2018), 2032–2055 | DOI | MR | Zbl

[31] Rui Ray Zhang, Xingwu Liu, Yuyi Wang, Liwei Wang, “McDiarmid-type inequalities for graph-dependent variables and stability bounds”, Advances in neural information processing systems 32 (NeurIPS 2019) (Vancouver, BC, 2019), MIT Press, Cambridge, MA, 2019, 10889–10899