Central limit theorems and bootstrap in high dimensions

In this paper, we derive central limit and bootstrap theorems for probabilities that centered high-dimensional vector sums hit rectangles and sparsely convex sets. Specifically, we derive Gaussian and bootstrap approximations for the probabilities that a root-n rescaled sample average of Xi is in A, where X1,..., Xn are independent random vectors in Rp and A is a rectangle, or, more generally, a sparsely convex set, and show that the approximation error converges to zero even if p=pn-> infinity and p>>n; in particular, p can be as large as O(e^(Cn^c)) for some constants c,C>0. The result holds uniformly over all rectangles, or more generally, sparsely convex sets, and does not require any restrictions on the correlation among components of Xi. Sparsely convex sets are sets that can be represented as intersections of many convex sets whose indicator functions depend nontrivially only on a small subset of their arguments, with rectangles being a special case.

[1]  D. Slepian.  The one-sided barrier problem for Gaussian noise , 1962 .

[2]  A. A. Borovkov,et al.  On the Multi-Dimensional Central Limit Theorem , 1965 .

[3]  C. Borell.  Convex measures on locally convex spaces , 1974 .

[4]  Rabindra N Bhattacharya.  On Errors of Normal Approximation , 1975 .

[5]  S. Nagaev.  An estimate of the remainder term in the multidimensional central limit theorem , 1976 .

[6]  R. Rao,et al.  Normal Approximation and Asymptotic Expansions , 1976 .

[7]  T. Sweeting.  Speeds of Convergence for the Multidimensional Central Limit Theorem , 1977 .

[8]  V. Sazonov.  Normal Approximation: Some Recent Advances , 1981 .

[9]  C. Stein.  Estimation of the Mean of a Multivariate Normal Distribution , 1981 .

[10]  E. Bolthausen.  An estimate of the remainder in a combinatorial central limit theorem , 1984 .

[11]  V. Bentkus.  Lower bounds for the rate of convergence in the central limit theorem in Banach spaces , 1985 .

[12]  Vidmantas Bentkus,et al.  Dependence of the Berry-Esseen estimate on the dimension , 1986 .

[13]  V. Milman,et al.  Asymptotic Theory Of Finite Dimensional Normed Spaces , 1986 .

[14]  F. Götze.  On the Rate of Convergence in the Multivariate CLT , 1991 .

[15]  M. Talagrand,et al.  Probability in Banach spaces , 1991 .

[16]  Keith Ball.  The reverse isoperimetric problem for Gaussian measure , 1993, Discret. Comput. Geom..

[17]  J. Wellner,et al.  Exchangeably Weighted Bootstraps of the General Empirical Process , 1993 .

[18]  Yosef Rinott,et al.  Multivariate normal approximations by Stein's method and size bias couplings , 1996 .

[19]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[20]  P. Massart,et al.  About the constants in Talagrand's concentration inequalities for empirical processes , 2000 .

[21]  A. W. van der Vaart,et al.  Uniform Central Limit Theorems , 2001 .

[22]  M. Talagrand,et al.  Spin Glasses: A Challenge for Mathematicians , 2003 .

[23]  V. Bentkus.  On the dependence of the Berry–Esseen bound on dimension , 2003 .

[24]  F. Nazarov.  On the Maximal Perimeter of a Convex Set in $ ℝ n $$\mathbb{R}^n$ with Respect to a Gaussian Measure , 2003 .

[25]  S. Chatterjee.  A simple invariance theorem , 2005, math/0508213.

[26]  U. Einmahl,et al.  Characterization of LIL behavior in Banach space , 2006, math/0608687.

[27]  S. Chatterjee,et al.  MULTIVARIATE NORMAL APPROXIMATION USING EXCHANGEABLE PAIRS , 2007, math/0701464.

[28]  Ryan O'Donnell,et al.  Learning Geometric Concepts via Gaussian Surface Area , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[29]  R. Adamczak,et al.  A Few Remarks on the Operator Norm of Random Toeplitz Matrices , 2008, 0803.3111.

[30]  Journal Url,et al.  A tail inequality for suprema of unbounded empirical processes with applications to Markov chains , 2008 .

[31]  G. Reinert,et al.  Multivariate normal approximation with Stein’s method of exchangeable pairs under a general linearity condition , 2007, 0711.1082.

[32]  Xiao Fang,et al.  Multivariate Normal Approximation by Stein's Method: The Concentration Inequality Approach , 2011, 1111.4073.

[33]  A. Barvinok.  Thrifty approximations of convex bodies by polytopes , 2012, 1206.3993.

[34]  Kengo Kato,et al.  Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors , 2012, 1212.6906.

[35]  D. Panchenko.  The Sherrington-Kirkpatrick Model , 2013 .

[36]  A. Röllin,et al.  Stein’s method in high dimensions with applications , 2011, 1101.4454.

[37]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[38]  Kengo Kato,et al.  Gaussian approximation of suprema of empirical processes , 2014 .

[39]  Comparison and anti-concentration bounds for maxima of Gaussian random vectors , 2015 .