Approximate Gibbs sampler for Bayesian Huberized lasso

被引:1
|
作者
Kawakami, Jun [1 ]
Hashimoto, Shintaro [1 ]
机构
[1] Hiroshima Univ, Dept Math, Higashihiroshima, Japan
关键词
Bayesian lasso; Gibbs sampler; Huber loss; robust regression; ROBUST REGRESSION; VARIABLE SELECTION; SCALE MIXTURES; SHRINKAGE; SPECIFICATION;
D O I
10.1080/00949655.2022.2096886
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The Bayesian lasso is well-known as a Bayesian alternative for Lasso. Although the advantage of the Bayesian lasso is capable of full probabilistic uncertain quantification for parameters, the corresponding posterior distribution can be sensitive to outliers. To overcome such problem, robust Bayesian regression models have been proposed in recent years. In this paper, we consider the robust and efficient estimation for the Bayesian Huberized lasso regression in fully Bayesian perspective. A new posterior computation algorithm for the Bayesian Huberized lasso regression is proposed. The proposed approximate Gibbs sampler is based on the approximation of full conditional distribution and it is possible to estimate a tuning parameter for robustness of the pseudo-Huber loss function. Some theoretical properties of the posterior distribution are also derived. We illustrate performance of the proposed method through simulation studies and real data examples.
引用
收藏
页码:128 / 162
页数:35
相关论文
共 50 条
  • [41] A CVAE-within-Gibbs sampler for Bayesian linear inverse problems with hyperparameters
    Yang, Jingya
    Niu, Yuanling
    Zhou, Qingping
    COMPUTATIONAL & APPLIED MATHEMATICS, 2023, 42 (03):
  • [42] Bayesian variable selection for latent class analysis using a collapsed Gibbs sampler
    White, Arthur
    Wyse, Jason
    Murphy, Thomas Brendan
    STATISTICS AND COMPUTING, 2016, 26 (1-2) : 511 - 527
  • [43] Bayesian Computation via the Gibbs Sampler for Mixture Models with Gaussian Distal Outcomes
    da Costa, Lilia C. C.
    Amorim, Leila D. A. F.
    Bispo, Gilmara S.
    STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL, 2021, 28 (06) : 839 - 850
  • [44] Bayesian hypothesis testing for the distribution of insurance claim counts using the Gibbs sampler
    Katsis, Athanassios
    Ntzoufras, Ioannis
    JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING, 2005, 5 (03) : 201 - 214
  • [45] T-wave Alternans Detection Using a Bayesian Approach and a Gibbs Sampler
    Lin, Chao
    Mailhes, Corinne
    Tourneret, Jean-Yves
    2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2011, : 5868 - 5871
  • [46] SUBSAMPLING THE GIBBS SAMPLER
    MACEACHERN, SN
    BERLINER, LM
    AMERICAN STATISTICIAN, 1994, 48 (03): : 188 - 190
  • [47] BAYESIAN-ESTIMATION IN MIXED LINEAR-MODELS USING THE GIBBS SAMPLER
    VANDERMERWE, AJ
    BOTHA, TJ
    SOUTH AFRICAN STATISTICAL JOURNAL, 1993, 27 (02) : 149 - 180
  • [48] The Polya-Gamma Gibbs sampler for Bayesian logistic regression is uniformly ergodic
    Choi, Hee Min
    Hobert, James P.
    ELECTRONIC JOURNAL OF STATISTICS, 2013, 7 : 2054 - 2064
  • [49] Bayesian variable selection for latent class analysis using a collapsed Gibbs sampler
    Arthur White
    Jason Wyse
    Thomas Brendan Murphy
    Statistics and Computing, 2016, 26 : 511 - 527
  • [50] The kernel Gibbs sampler
    Graepel, T
    Herbrich, R
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 13, 2001, 13 : 514 - 520