Spectral Detection in the Censored Block Model

被引：0
|
作者：
Saade, Alaa [1 ]
Krzakala, Florent [2 ]
Lelarge, Marc [3 ,4 ]
Zdeborova, Lenka [5 ,6 ]
机构：
[1] Ecole Normale Super, Lab Phys Stat, 24 Rue Lhomond, F-75005 Paris, France
[2] Univ Paris 06, CNRS UMR 8550, Ecole Normale Super, Sorbonne Univ,Lab Phys Stat, Paris, France
[3] INRIA, Paris, France
[4] Ecole Normale Super, Paris, France
[5] CEA Saclay, Inst Phys Theor, F-91191 Gif Sur Yvette, France
[6] CNRS, URA 2306, F-91191 Gif Sur Yvette, France
来源：
2015 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT) | 2015年
关键词：
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
We consider the problem of partially recovering hidden binary variables from the observation of (few) censored edge weights, a problem with applications in community detection, correlation clustering and synchronization. We describe two spectral algorithms for this task based on the non-backtracking and the Bethe Hessian operators. These algorithms are shown to be asymptotically optimal for the partial recovery problem, in that they detect the hidden assignment as soon as it is information theoretically possible to do so.
引用
收藏
页码：1184 / 1188
页数：5
相关论文
共 50 条
  • [1] Spectral recovery of binary censored block models
    Dhara, Souvik
    Gaudio, Julia
    Mossel, Elchanan
    Sandon, Colin
    [J]. PROCEEDINGS OF THE 2022 ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, SODA, 2022, : 3389 - 3416
  • [2] Exact Recovery Threshold in the Binary Censored Block Model
    Hajek, Bruce
    Wu, Yihong
    Xu, Jiaming
    [J]. 2015 IEEE INFORMATION THEORY WORKSHOP - FALL (ITW), 2015, : 99 - 103
  • [3] Limiting spectral distribution of stochastic block model
    Su, Giap Van
    Chen, May-Ru
    Guo, Mei-Hui
    Huang, Hao-Wei
    [J]. RANDOM MATRICES-THEORY AND APPLICATIONS, 2023, 12 (04)
  • [4] Spectral clustering in the dynamic stochastic block model
    Pensky, Marianna
    Zhang, Teng
    [J]. ELECTRONIC JOURNAL OF STATISTICS, 2019, 13 (01): : 678 - 709
  • [5] Adaptive Path Interpolation Method for Sparse Systems: Application to a Censored Block Model
    Barbier, Jean
    Chan, Chun Lam
    Macris, Nicolas
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2021, 67 (04) : 2093 - 2114
  • [6] Adaptive Path Interpolation for Sparse Systems: Application to a Simple Censored Block Model
    Barbier, Jean
    Chan, Chun Lam
    Macris, Nicolas
    [J]. 2018 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2018, : 1879 - 1883
  • [7] Model averaging quantiles from data censored by a limit of detection
    Nysen, Ruth
    Faes, Christel
    Ferrari, Pietro
    Verger, Philippe
    Aerts, Marc
    [J]. BIOMETRICAL JOURNAL, 2016, 58 (02) : 331 - 356
  • [8] A censored random coefficients model for the detection of zero willingness to pay
    Reichl, Johannes
    Fruehwirth-Schnatter, Sylvia
    [J]. QME-QUANTITATIVE MARKETING AND ECONOMICS, 2012, 10 (02): : 259 - 281
  • [9] A censored random coefficients model for the detection of zero willingness to pay
    Johannes Reichl
    Sylvia Frühwirth-Schnatter
    [J]. Quantitative Marketing and Economics, 2012, 10 : 259 - 281
  • [10] CENSORED OBSERVATIONS IN RANDOMIZED BLOCK EXPERIMENTS
    SAMPFORD, MR
    TAYLOR, J
    [J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1959, 21 (01) : 214 - 237
12345