Testing for Anomalies: Active Strategies and Non-asymptotic Analysis

被引：0
|
作者：
Kartik, Dhruva [1 ]
Nayyar, Ashutosh [1 ]
Mitra, Urbashi [1 ]
机构：
[1] Univ Southern Calif, Ming Hsieh Dept Elect & Comp Engn, Los Angeles, CA 90007 USA
来源：
2020 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT) | 2020年
基金：
美国国家科学基金会;
关键词：
D O I：
10.1109/isit44484.2020.9174399
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
The problem of verifying whether a multicomponent system has anomalies or not is addressed. Each component can be probed over time in a data-driven manner to obtain noisy observations that indicate whether the selected component is anomalous or not. The aim is to minimize the probability of incorrectly declaring the system to be free of anomalies while ensuring that the probability of correctly declaring it to be safe is sufficiently large. This problem is modeled as an active hypothesis testing problem in the Neyman-Pearson setting. Component-selection and inference strategies are designed and analyzed in the non-asymptotic regime. For a specific class of homogeneous problems, stronger (with respect to prior work) non-asymptotic converse and achievability bounds are provided.
引用
收藏
页码：1277 / 1282
页数：6
相关论文
共 50 条
  • [1] Non-asymptotic minimax rates of testing in signal detection
    Baraud, Y
    BERNOULLI, 2002, 8 (05) : 577 - 606
  • [2] Non-asymptotic analysis of tangent space perturbation
    Kaslovsky, Daniel N.
    Meyer, Francois G.
    INFORMATION AND INFERENCE-A JOURNAL OF THE IMA, 2014, 3 (02) : 134 - 187
  • [3] Non-asymptotic calibration and resolution
    Vovk, V
    ALGORITHMIC LEARNING THEORY, 2005, 3734 : 429 - 443
  • [4] Non-Asymptotic Analysis for Relational Learning with One Network
    He, Peng
    Zhang, Changshui
    ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 33, 2014, 33 : 320 - 327
  • [5] Feedback in the Non-Asymptotic Regime
    Polyanskiy, Yury
    Poor, H. Vincent
    Verdu, Sergio
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2011, 57 (08) : 4903 - 4925
  • [6] Non-asymptotic Analysis of Biased Stochastic Approximation Scheme
    Karimi, Belhal
    Miasojedow, Blazej
    Moulines, Eric
    Wai, Hoi-To
    CONFERENCE ON LEARNING THEORY, VOL 99, 2019, 99
  • [7] Language Approximation: Asymptotic and Non-asymptotic Results
    Ravikumar, Bala
    DEVELOPMENTS IN LANGUAGE THEORY, DLT 2017, 2017, 10396
  • [8] Non-asymptotic sub-Gaussian error bounds for hypothesis testing
    Li, Yanpeng
    Tian, Boping
    STATISTICS & PROBABILITY LETTERS, 2022, 189
  • [9] Non-Asymptotic Analysis of Monte Carlo Tree Search
    Shah D.
    Xie Q.
    Xu Z.
    Performance Evaluation Review, 2020, 48 (01): : 31 - 32
  • [10] Non-asymptotic thermodynamic ensembles
    Niven, R. K.
    EPL, 2009, 86 (02)
12345