Abstract
A central tool in the study of nonhomogeneous random matrices, the noncommutative Khintchine inequality, yields a nonasymptotic bound on the spectral norm of general Gaussian random matrices \(X=\sum _{i} g_{i} A_{i}\) where \(g_{i}\) are independent standard Gaussian variables and \(A_{i}\) are matrix coefficients. This bound exhibits a logarithmic dependence on dimension that is sharp when the matrices \(A_{i}\) commute, but often proves to be suboptimal in the presence of noncommutativity. In this paper, we develop nonasymptotic bounds on the spectrum of arbitrary Gaussian random matrices that can capture noncommutativity. These bounds quantify the degree to which the spectrum of \(X\) is captured by that of a noncommutative model \(X_{\mathrm{free}}\) that arises from free probability theory. This “intrinsic freeness” phenomenon provides a powerful tool for the study of various questions that are outside the reach of classical methods of random matrix theory. Our nonasymptotic bounds are easily applicable in concrete situations, and yield sharp results in examples where the noncommutative Khintchine inequality is suboptimal. When combined with a linearization argument, our bounds imply strong asymptotic freeness for a remarkably general class of Gaussian random matrix models that may be very sparse, have dependent entries, and lack any special symmetries. When combined with a universality principle, our bounds extend beyond the Gaussian setting to general sums of independent random matrices.
Similar content being viewed by others
Notes
We write \(x\lesssim y\) if \(x\le Cy\) for a universal constant \(C\), and \(x\asymp y\) if \(x\lesssim y\) and \(y\lesssim x\).
Throughout this section ⊗ always denotes the minimal tensor product of \(C^{*}\)-algebras.
References
Alt, J., Erdős, L., Krüger, T.: The Dyson equation with linear self-energy: spectral bands, edges and cusps. Doc. Math. 25, 1421–1539 (2020)
Anderson, G.W., Guionnet, A., Zeitouni, O.: An Introduction to Random Matrices. Cambridge Studies in Advanced Mathematics, vol. 118. Cambridge University Press, Cambridge (2010)
Au, B.: Traffic distributions of random band matrices. Electron. J. Probab. 23, Paper No. 77, 48 (2018)
Bai, Z.D., Yin, Y.Q.: Limit of the smallest eigenvalue of a large-dimensional sample covariance matrix. Ann. Probab. 21(3), 1275–1294 (1993)
Bandeira, A.S.: Ten lectures and forty-two open problems in the mathematics of data science. Lecture notes (2015)
Bandeira, A.S., van Handel, R.: Sharp nonasymptotic bounds on the norm of random matrices with independent entries. Ann. Probab. 44(4), 2479–2506 (2016)
Belinschi, S., Capitaine, M.: Strong convergence of tensor products of independent GUE matrices. Preprint (2022). arXiv:2205.07695
Bordenave, C., Collins, B.: Strong asymptotic freenes for independent uniform variables on compact groups associated to non-trivial representations. Preprint (2020). arXiv:2012.08759
Bose, A.: Patterned Random Matrices. CRC Press, Boca Raton (2018)
Brailovskaya, T., van Handel, R.: Universality and sharp matrix concentration inequalities. Preprint (2022). arXiv:2201.05142
Cai, T.T., Han, R., Zhang, A.R.: On the non-asymptotic concentration of heteroskedastic Wishart-type matrix. Electron. J. Probab. 27, Paper No. 29, 40 (2022)
Calderón, A.-P.: Intermediate spaces and interpolation, the complex method. Stud. Math. 24, 113–190 (1964)
Collins, B., Male, C.: The strong asymptotic freeness of Haar and deterministic matrices. Ann. Sci. Éc. Norm. Supér. (4) 47(1), 147–163 (2014)
Collins, B., Guionnet, A., Parraud, F.: On the operator norm of non-commutative polynomials in deterministic matrices and iid GUE matrices. Camb. J. Math. 10(1), 195–260 (2022)
Davidson, K.R., Szarek, S.J.: Local operator theory, random matrices and Banach spaces. In: Handbook of the Geometry of Banach Spaces, vol. I, pp. 317–366. North-Holland, Amsterdam (2001)
Erdős, L., Mühlbacher, P.: Bounds on the norm of Wigner-type random matrices. Random Matrices: Theory Appl. 8(3), 1950009, 28 (2019)
Fleermann, M., Kirsch, W., Kriecherbauer, T.: The almost sure semicircle law for random band matrices with dependent entries. Stoch. Process. Appl. 131, 172–200 (2021)
Gantmacher, F.R.: The Theory of Matrices, vol. 2. Chelsea, New York (1959). Translated by K.A. Hirsch
Haagerup, U., Thorbjørnsen, S.: Random matrices and \(K\)-theory for exact \(C^{\ast}\)-algebras. Doc. Math. 4, 341–450 (1999)
Haagerup, U., Thorbjørnsen, S.: A new application of random matrices: \({\mathrm{Ext}}(C^{*}_{\mathrm{red}}(F_{2}))\) is not a group. Ann. Math. (2) 162(2), 711–775 (2005)
Haagerup, U., Schultz, H., Thorbjørnsen, S.: A random matrix approach to the lack of projections in \(C^{*}_{\mathrm{red}}(\mathbb{F}_{2})\). Adv. Math. 204(1), 1–83 (2006)
Hayes, B.: A random matrix approach to the Peterson-Thom conjecture. Indiana Univ. Math. J. 71(3), 1243–1297 (2022)
Koltchinskii, V., Lounici, K.: Concentration inequalities and moment bounds for sample covariance operators. Bernoulli 23(1), 110–133 (2017)
Latała, R., van Handel, R., Youssef, P.: The dimension-free structure of nonhomogeneous random matrices. Invent. Math. 214(3), 1031–1080 (2018)
Ledoux, M.: The Concentration of Measure Phenomenon. Mathematical Surveys and Monographs, vol. 89. Am. Math. Soc., Providence (2001)
Ledoux, M., Talagrand, M.: Probability in Banach Spaces: Isoperimetry and Processes. Ergebnisse der Mathematik und ihrer Grenzgebiete (3) [Results in Mathematics and Related Areas (3)], vol. 23. Springer, Berlin (1991)
Lehner, F.: Computing norms of free operators with matrix coefficients. Am. J. Math. 121(3), 453–486 (1999)
Mingo, J.A., Speicher, R.: Free Probability and Random Matrices. Fields Institute Monographs, vol. 35. Springer, New York; Fields Institute for Research in Mathematical Sciences, Toronto (2017)
Nica, A., Speicher, R.: Lectures on the Combinatorics of Free Probability. London Mathematical Society Lecture Note Series, vol. 335. Cambridge University Press, Cambridge (2006)
Parraud, F.: Asymptotic expansion of smooth functions in polynomials in deterministic matrices and iid GUE matrices. Commun. Math. Phys. 399(1), 249–294 (2023)
Pisier, G.: Introduction to Operator Space Theory. London Mathematical Society Lecture Note Series, vol. 294. Cambridge University Press, Cambridge (2003)
Pisier, G., Xu, Q.: Non-commutative \(L^{p}\)-spaces. In: Handbook of the Geometry of Banach Spaces, vol. 2, pp. 1459–1517. North-Holland, Amsterdam (2003)
Rudelson, M.: Random vectors in the isotropic position. J. Funct. Anal. 164(1), 60–72 (1999)
Rudelson, M., Zeitouni, O.: Singular values of Gaussian matrices and permanent estimators. Random Struct. Algorithms 48(1), 183–212 (2016)
Schultz, H.: Non-commutative polynomials of independent Gaussian random matrices. The real and symplectic cases. Probab. Theory Relat. Fields 131(2), 261–309 (2005)
Shlyakhtenko, D.: Random Gaussian band matrices and freeness with amalgamation. Int. Math. Res. Not. 20, 1013–1025 (1996)
Talagrand, M.: Mean Field Models for Spin Glasses. Volume I: Basic Examples. Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge. A Series of Modern Surveys in Mathematics [Results in Mathematics and Related Areas. 3rd Series. A Series of Modern Surveys in Mathematics], vol. 54. Springer, Berlin (2011)
Tao, T.: Topics in Random Matrix Theory. Graduate Studies in Mathematics, vol. 132. Am. Math. Soc., Providence (2012)
Tropp, J.A.: An introduction to matrix concentration inequalities. Found. Trends Mach. Learn. 8, 1–230 (2015)
Tropp, J.A.: The expected norm of a sum of independent random matrices: an elementary approach. In: High Dimensional Probability VII. Progr. Probab., vol. 71, pp. 173–202. Springer, Cham (2016)
Tropp, J.A.: Second-order matrix concentration inequalities. Appl. Comput. Harmon. Anal. 44(3), 700–736 (2018)
van Handel, R.: On the spectral norm of Gaussian random matrices. Trans. Am. Math. Soc. 369(11), 8161–8178 (2017)
van Handel, R.: Structured random matrices. In: Convexity and Concentration. IMA Vol. Math. Appl., vol. 161, pp. 107–156. Springer, New York (2017)
Voiculescu, D.: Limit laws for random matrices and free products. Invent. Math. 104(1), 201–220 (1991)
Acknowledgements
The authors thank Benson Au, Tatiana Brailovskaya, Ioana Dumitriu, Antti Knowles, Gilles Pisier, Mark Rudelson, Dominik Schröder, Joel Tropp, Nikita Zhivotovskiy, and Yizhe Zhu for interesting discussions, and the referees for helpful suggestions and feedback.
Funding
M.T.B. was supported in part by NSF grant DMS-1856221, and the NSF-Simons Collaboration on Theoretical Foundations of Deep Learning. R.v.H. was supported in part by NSF grants DMS-1811735 and DMS-2054565, and the Simons Collaboration on Algorithms & Geometry.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bandeira, A.S., Boedihardjo, M.T. & van Handel, R. Matrix concentration inequalities and free probability. Invent. math. 234, 419–487 (2023). https://doi.org/10.1007/s00222-023-01204-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00222-023-01204-6