A high-dimensional CLT in W2 distance with near optimal convergence rate

被引:0
|
作者
Zhai, Alex [1 ]
机构
[1] Stanford Univ, Stanford, CA 94305 USA
关键词
CENTRAL-LIMIT-THEOREM; TRANSPORTATION COST; BOUNDS;
D O I
10.1007/s00440-017-0771-3
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Let X-1, ... , X-n be i.i.d. random vectors in R-d with parallel to X-1 parallel to <= beta. Then, we show that 1/root n (X-1 + ... + X-n) converges to a Gaussian in quadratic transportation (also known as "Kantorovich" or "Wasserstein") distance at a rate of O(root d beta log n/root n), improving a result of Valiant and Valiant. The main feature of our theorem is that the rate of convergence is within log n of optimal for n, d -> infinity.
引用
收藏
页码:821 / 845
页数:25
相关论文
共 50 条
  • [41] The growth rate of high-dimensional tree polycubes
    Aleksandrowicz, Gadi
    Barequet, Gill
    [J]. EUROPEAN JOURNAL OF COMBINATORICS, 2014, 35 : 32 - 38
  • [42] Optimal recovery of precision matrix for Mahalanobis distance from high-dimensional noisy observations in manifold learning
    Gavish, Matan
    Su, Pei-Chun
    Talmon, Ronen
    Wu, Hau-Tieng
    [J]. INFORMATION AND INFERENCE-A JOURNAL OF THE IMA, 2022, 11 (04) : 1173 - 1202
  • [43] On Asymptotic Behaviour and W2,p Regularity of Potentials in Optimal Transportation
    Liu, Jiakun
    Trudinger, Neil S.
    Wang, Xu-Jia
    [J]. ARCHIVE FOR RATIONAL MECHANICS AND ANALYSIS, 2015, 215 (03) : 867 - 905
  • [44] Improved visualization of high-dimensional data using the distance-of-distance transformation
    Liu, Jinke
    Vinck, Martin
    [J]. PLOS COMPUTATIONAL BIOLOGY, 2022, 18 (12)
  • [45] On Asymptotic Behaviour and W2, p Regularity of Potentials in Optimal Transportation
    Jiakun Liu
    Neil S. Trudinger
    Xu-Jia Wang
    [J]. Archive for Rational Mechanics and Analysis, 2015, 215 : 867 - 905
  • [46] A RATE OPTIMAL PROCEDURE FOR RECOVERING SPARSE DIFFERENCES BETWEEN HIGH-DIMENSIONAL MEANS UNDER DEPENDENCE
    Li, Jun
    Zhong, Ping-Shou
    [J]. ANNALS OF STATISTICS, 2017, 45 (02): : 557 - 590
  • [47] CONVERGENCE AND PREDICTION OF PRINCIPAL COMPONENT SCORES IN HIGH-DIMENSIONAL SETTINGS
    Lee, Seunggeun
    Zou, Fei
    Wright, Fred A.
    [J]. ANNALS OF STATISTICS, 2010, 38 (06): : 3605 - 3629
  • [48] CONVERGENCE OF A GREEDY ALGORITHM FOR HIGH-DIMENSIONAL CONVEX NONLINEAR PROBLEMS
    Cances, Eric
    Ehrlacher, Virginie
    Lelievre, Tony
    [J]. MATHEMATICAL MODELS & METHODS IN APPLIED SCIENCES, 2011, 21 (12): : 2433 - 2467
  • [49] Mapping high-dimensional data onto a relative distance plane - an exact method for visualizing and characterizing high-dimensional patterns
    Somorjai, RL
    Dolenko, B
    Demko, A
    Mandelzweig, M
    Nikulin, AE
    Baumgartner, R
    Pizzi, NJ
    [J]. JOURNAL OF BIOMEDICAL INFORMATICS, 2004, 37 (05) : 366 - 379
  • [50] The Optimal Convergence Rate of Monotone Schemes for Conservation Laws in the Wasserstein Distance
    Adrian M. Ruf
    Espen Sande
    Susanne Solem
    [J]. Journal of Scientific Computing, 2019, 80 : 1764 - 1776