Non-asymptotic sub-Gaussian error bounds for hypothesis testing

被引:0
|
作者
Li, Yanpeng [1 ]
Tian, Boping [1 ]
机构
[1] Harbin Inst Technol, Sch Math, Harbin 150001, Peoples R China
关键词
Pinskers bound; KL divergence; Sub-Gaussian; Fanos inequality;
D O I
10.1016/j.spl.2022.109586
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
Using the sub-Gaussian norm of the Bernoulli random variable, this paper presents the explicit and informative error lower bounds for binary and multiple hypothesis testing in terms of the KL divergence non-asymptotically. Some numerical comparisons are also demonstrated. (C) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页数:5
相关论文
共 50 条
  • [41] Non-asymptotic upper bounds on the probability of the ε-atypical set for Markov chains
    Lastras-Montaño, LA
    2004 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, PROCEEDINGS, 2004, : 222 - 222
  • [42] Non-Asymptotic Bounds on Fixed Length Source Coding for Markov Chains
    Hayashi, Masahito
    Watanabe, Shun
    2013 51ST ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2013, : 875 - 882
  • [43] Sharp sub-Gaussian upper bounds for subsolutions of Trudinger's equation on Riemannian manifolds
    Suerig, Philipp
    NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2024, 249
  • [44] Non-Asymptotic Bounds on the Performance of Dual Methods for Resource Allocation Problems
    Goertzen, Simon
    Schmeink, Anke
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2014, 13 (06) : 3430 - 3441
  • [45] Recent advances in scalable non-Gaussian geostatistics: The generalized sub-Gaussian model
    Guadagnini, Alberto
    Riva, Monica
    Neuman, Shlomo P.
    JOURNAL OF HYDROLOGY, 2018, 562 : 685 - 691
  • [46] Non-asymptotic Gaussian estimates for the recursive approximation of the invariant distribution of a diffusion
    Honor, I
    Menozzi, S.
    Pages, G.
    ANNALES DE L INSTITUT HENRI POINCARE-PROBABILITES ET STATISTIQUES, 2020, 56 (03): : 1559 - 1605
  • [47] A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits
    Barrier, Antoine
    Garivier, Aurelien
    Kocak, Tomas
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [48] Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems
    Tapio Helin
    Remo Kretschmann
    Numerische Mathematik, 2022, 150 : 521 - 549
  • [49] THE PERTURBED PROX-PRECONDITIONED SPIDER ALGORITHM: NON-ASYMPTOTIC CONVERGENCE BOUNDS
    Fort, G.
    Moulines, E.
    2021 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), 2021, : 96 - 100
  • [50] Non-Asymptotic Converse Bounds and Refined Asymptotics for Two Source Coding Problems
    Zhou, Lin
    Motani, Mehul
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2019, 65 (10) : 6414 - 6440