Abstract
In contemporary applied and computational mathematics, a frequent challenge is to bound the expectation of the spectral norm of a sum of independent random matrices. This quantity is controlled by the norm of the expected square of the random matrix and the expectation of the maximum squared norm achieved by one of the summands; there is also a weak dependence on the dimension of the random matrix. The purpose of this paper is to give a complete, elementary proof of this important inequality.
Mathematics Subject Classification (2010). 60B20; 60F10, 60G50, 60G42
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
A. Bandeira, R.V. Handel, Sharp nonasymptotic bounds on the norm of random matrices with independent entries (2014). Available at http://arXiv.org/abs/1408.6185
R.F. Bass, K. Gröchenig, Relevant sampling of band-limited functions. Ill. J. Math. 57 (1), 43–58 (2013)
R. Bhatia, Matrix Analysis. Graduate Texts in Mathematics, vol. 169 (Springer, New York, 1997)
S. Boucheron, G. Lugosi, P. Massart, Concentration Inequalities (Oxford University Press, Oxford, 2013). A nonasymptotic theory of independence, With a foreword by Michel Ledoux
A. Buchholz, Operator Khintchine inequality in non-commutative probability. Math. Ann. 319 (1), 1–16 (2001)
X. Chen, T.M. Christensen, Optimal uniform convergence rates for sieve nonparametric instrumental variables regression (2013). Available at http://arXiv.org/abs/1311.0412
R.Y. Chen, A. Gittens, J.A. Tropp, The masked sample covariance estimator: an analysis using matrix concentration inequalities. Inf. Inference 1 (1), 2–20 (2012)
Y. Chen, S. Bhojanapalli, S. Sanghavi, R. Ward, Coherent matrix completion, in Proceedings of the 31st International Conference on Machine Learning, Beijing (2014)
Y. Chen, L. Guibas, Q. Huang, Near-optimal joint object matching via convex relaxation, in Proceedings of the 31st International Conference on Machine Learning, Beijing (2014)
S.-S. Cheung, A.M.-C. So, K. Wang, Linear matrix inequalities with stochastically dependent perturbations and applications to chance-constrained semidefinite optimization. SIAM J. Optim. 22 (4), 1394–1430 (2012)
A. Cohen, M.A. Davenport, D. Leviatan, On the stability and accuracy of least squares approximations. Found. Comput. Math. 13 (5), 819–834 (2013)
M.B. Cohen, R. Kyng, G.L. Miller, J.W. Pachocki, R. Peng, A.B. Rao, S.C. Xu, Solving SDD linear systems in nearly mlog1∕2(n) time, in Proceedings of the 46th Annual ACM Symposium on Theory of Computing, STOC ’14 (ACM, New York, 2014), pp. 343–352
P. Constantine, D. Gleich, Computing active subspaces (2014). Available at http://arXiv.org/abs/1408.0545
S. Dirksen, Itô isomorphisms for L p-valued Poisson stochastic integrals. Ann. Probab. 42 (6), 2595–2643 (2014)
J. Djolonga, A. Krause, V. Cevher, High-dimensional Gaussian process bandits, in Advances in Neural Information Processing Systems, vol. 26, ed. by C. Burges, L. Bottou, M. Welling, Z. Ghahramani, K. Weinberger (Curran Associates, Inc., Red Hook, 2013), pp. 1025–1033
M. Fornasier, K. Schnass, J. Vybiral, Learning functions of few arbitrary linear parameters in high dimensions. Found. Comput. Math. 12 (2), 229–262 (2012)
N.J.A. Harvey, N. Olver, Pipage rounding, pessimistic estimators and matrix concentration, in Proceedings of the Twenty-Fifth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA ’14 (SIAM, Philadelphia, 2014), pp. 926–945
A.S. Holevo, Quantum systems, channels, information, in De Gruyter Studies in Mathematical Physics, vol. 16 (De Gruyter, Berlin, 2012). A Mathematical Introduction
R.A. Horn, C.R. Johnson, Matrix Analysis, 2nd edn. (Cambridge University Press, Cambridge, 2013)
M. Junge, Q. Xu, Noncommutative Burkholder/Rosenthal inequalities. Ann. Probab. 31 (2), 948–995 (2003)
M. Junge, Q. Xu, Noncommutative Burkholder/Rosenthal inequalities. II. Applications. Isr. J. Math. 167, 227–282 (2008)
M. Junge, Q. Zeng, Noncommutative Bennett and Rosenthal inequalities. Ann. Probab. 41 (6), 4287–4316 (2013)
V. Koltchinskii, Oracle Inequalities in Empirical Risk Minimization and Sparse Recovery Problems. Lecture Notes in Mathematics, vol. 2033 (Springer, Heidelberg, 2011). Lectures from the 38th Probability Summer School held in Saint-Flour, 2008, École d’Été de Probabilités de Saint-Flour. [Saint-Flour Probability Summer School]
R. Latała, K. Oleszkiewicz, On the best constant in the Khinchin-Kahane inequality. Stud. Math., 109 (1), 101–104 (1994)
M. Ledoux, M. Talagrand, Probability in Banach Spaces. Classics in Mathematics (Springer, Berlin, 2011). Isoperimetry and Processes, reprint of the 1991 edition
D. Lopez-Paz, S. Sra, A. Smola, Z. Ghahramani, B. Schölkopf, Randomized nonlinear component analysis, in Proceedings of the 31st International Conference on Machine Learning, Beijing (2014)
F. Lust-Piquard, Inégalités de Khintchine dans C p (1 < p < ∞). C. R. Acad. Sci. Paris Sér. I Math. 303 (7), 289–292 (1986)
L. Mackey, M.I. Jordan, R.Y. Chen, B. Farrell, J.A. Tropp, Matrix concentration inequalities via the method of exchangeable pairs. Ann. Probab. 42 (3), 906–945 (2014)
A. Magen, A. Zouzias, Low rank matrix-valued Chernoff bounds and approximate matrix multiplication, in Proceedings of the Twenty-Second Annual ACM-SIAM Symposium on Discrete Algorithms (SIAM, Philadelphia, PA, 2011), pp. 1422–1436
W.B. March, G. Biros, Far-field compression for fast kernel summation methods in high dimensions (2014). Available at http://arXiv.org/abs/1409.2802
E. Morvant, S. Koço, L. Ralaivola, PAC-Bayesian generalization bound on confusion matrix for multi-class classification, in Proceedings of the 29th International Conference on Machine Learning, Edinburgh (2012)
S.V. Nagaev, I.F. Pinelis, Some inequalities for the distributions of sums of independent random variables. Teor. Verojatnost. i Primenen. 22 (2), 254–263 (1977)
R.I. Oliveira, The spectrum of random k-lifts of large graphs (with possibly large k). J. Comb. 1 (3–4), 285–306 (2010)
R.I. Oliveira, The lower tail of random quadratic forms, with applications to ordinary least squares and restricted eigenvalue properties (2013). Available at http://arXiv.org/abs/1312.2903
D. Paulin, L. Mackey, J.A. Tropp, Efron–Stein inequalities for random matrices. Ann. Probab. (2015, to appear). Available at http://arXiv.org/abs/1408.3470
G. Pisier, Non-commutative vector valued L p -spaces and completely p-summing maps. Astérisque 247, vi+131 (1998)
B. Rosén, On bounds on the central moments of even order of a sum of independent random variables. Ann. Math. Stat. 41, 1074–1077 (1970)
H.P. Rosenthal, On the subspaces of L p ( p > 2) spanned by sequences of independent random variables. Isr. J. Math. 8, 273–303 (1970)
M. Rudelson, Random vectors in the isotropic position. J. Funct. Anal. 164 (1), 60–72 (1999)
M. Rudelson, R. Vershynin, Sampling from large matrices: an approach through geometric functional analysis. J. ACM 54 (4), Art. 21, 19 pp. (electronic) (2007)
J.A. Tropp, On the conditioning of random subdictionaries. Appl. Comput. Harmon. Anal. 25 (1), 1–24 (2008)
J.A. Tropp, Improved analysis of the subsampled randomized Hadamard transform. Adv. Adapt. Data Anal. 3 (1–2), 115–126 (2011)
J.A. Tropp, The expected norm of a sum of independent random matrices: an elementary approach (2015). Available at http://arXiv.org/abs/1506.04711
J.A. Tropp, An introduction to matrix concentration inequalities. Found. Trends Mach. Learn. 8 (1–2), 1–230 (2015)
J.A. Tropp, Second-order matrix concentration inequalities (2015). Available at http://arXiv.org/abs/1504.05919
Acknowledgements
The author wishes to thank Ryan Lee for a careful reading of the manuscript. The author gratefully acknowledges support from ONR award N00014-11-1002 and the Gordon & Betty Moore Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Tropp, J.A. (2016). The Expected Norm of a Sum of Independent Random Matrices: An Elementary Approach. In: Houdré, C., Mason, D., Reynaud-Bouret, P., Rosiński, J. (eds) High Dimensional Probability VII. Progress in Probability, vol 71. Birkhäuser, Cham. https://doi.org/10.1007/978-3-319-40519-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-40519-3_8
Published:
Publisher Name: Birkhäuser, Cham
Print ISBN: 978-3-319-40517-9
Online ISBN: 978-3-319-40519-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)