Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors

Research, Preprint, Other literature type English OPEN
Chernozhukov, Victor; Chetverikov, Denis; Kato, Kengo;
(2012)
  • Publisher: The Institute of Mathematical Statistics
  • Journal: issn: 0090-5364
  • Related identifiers: doi: 10.1214/13-AOS1161, doi: 10.1920/wp.cem.2013.7613
  • Subject: Mathematics - Statistics Theory | maximum of vector sums | Economics - Econometrics | Dantzig selector | high dimensionality | 62F40 | Mathematics - Probability | Slepian | anti-concentration | 62E17 | Stein method
    • ddc: ddc:330

We derive a Gaussian approximation result for the maximum of a sum of high-dimensional random vectors. Specifically, we establish conditions under which the distribution of the maximum is approximated by that of the maximum of a sum of the Gaussian random vectors with t... View more
  • References (35)
    35 references, page 1 of 4

    Lemma I.1 (A Simple Comparison of Gaussian to Non-Gaussian Max-

    ima). For every g 2 Cb3(R) and > 0,

    1m6ja6xp (|xij | + |yij |)3 ,

    1 log p +

    1 + p c)p1 _ log(p )⇤ [1] Asriev, A.V. and Rotar, V.I. (1989). On the convergence rate in the infinite-

    of Probability and Its Applications 30 691-701. [2] Ball, K. (1993). The reverse isoperimetric problem for Gaussian measure. Discrete

    Comput. Geom. 10 411-420. [3] Bentkus, V. (1990). Smooth approximations of the norm and di↵erentiable functions

    with bounded support in Banach space l1k . Lith. Math. Journal 30 223-230. [4] Bentkus, V. (2003). On the dependence of the Berry-Esseen bound on dimension. J.

    Statist. Plann. Infer. 113 385-402. [5] Bentkus, V., Go¨tze, F., Paulauskas, V., and Rackauskus, L. (2000). The accuracy of

    (Eds. Y.V. Prokholov and V. Statuleviˇcius), Springer, pp. 25-111. [6] Chatterjee, S. (2005a). A simple invariance theorem. arXiv:math/0508213. [7] Chatterjee, S. (2006). A generalization of Lindeberg's principle. Ann. Probab. 34

  • Similar Research Results (1)
  • Metrics
    No metrics available
Share - Bookmark