Hanson-Wright inequality and sub-gaussian concentration

被引:274
|
作者
Rudelson, Mark [1 ]
Vershynin, Roman [1 ]
机构
[1] Univ Michigan, Ann Arbor, MI 48109 USA
基金
美国国家科学基金会;
关键词
subgaussian random variables; concentration inequalities; random matrices; TAIL PROBABILITIES;
D O I
10.1214/ECP.v18-2865
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
In this expository note, we give a modern proof of Hanson-Wright inequality for quadratic forms in sub-gaussian random variables. We deduce a useful concentration inequality for sub-gaussian random vectors. Two examples are given to illustrate these results: a concentration of distances between random vectors and subspaces, and a bound on the norms of products of random and deterministic matrices.
引用
收藏
页码:1 / 9
页数:9
相关论文
共 50 条
  • [1] Sparse Hanson-Wright inequality for a bilinear form of sub-Gaussian variables
    Park, Seongoh
    Wang, Xinlei
    Lim, Johan
    STAT, 2023, 12 (01):
  • [2] Hanson-Wright inequality in Banach spaces
    Adamczak, Radoslaw
    Latala, Rafal
    Meller, Rafal
    ANNALES DE L INSTITUT HENRI POINCARE-PROBABILITES ET STATISTIQUES, 2020, 56 (04): : 2356 - 2376
  • [3] The Hanson-Wright inequality for random tensors
    Bamberger, Stefan
    Krahmer, Felix
    Ward, Rachel
    SAMPLING THEORY SIGNAL PROCESSING AND DATA ANALYSIS, 2022, 20 (02):
  • [4] A note on the Hanson-Wright inequality for random vectors with dependencies
    Adamczak, Radoslaw
    ELECTRONIC COMMUNICATIONS IN PROBABILITY, 2015, 20
  • [5] Sub-gaussian inequality on tent spaces
    Labeye-Voisin, E
    STUDIA MATHEMATICA, 2003, 155 (01) : 23 - 36
  • [7] Sparse Hanson-Wright inequalities for subgaussian quadratic forms
    Zhou, Shuheng
    BERNOULLI, 2019, 25 (03) : 1603 - 1639
  • [8] Uniform Hanson-Wright type concentration inequalities for unbounded entries via the entropy method
    Klochkov, Yegor
    Zhivotovskiy, Nikita
    ELECTRONIC JOURNAL OF PROBABILITY, 2020, 25
  • [9] Hanson-Wright inequality in Hilbert spaces with application to K-means clustering for non-Euclidean data
    Chen, Xiaohui
    Yang, Yun
    BERNOULLI, 2021, 27 (01) : 586 - 614
  • [10] Concentration inequalities under sub-Gaussian and sub-exponential conditions
    Maurer, Andreas
    Pontil, Massimiliano
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34