ANOVA-GP Modeling for High-Dimensional Bayesian Inverse Problems

被引:0
|
作者
Shi, Xiaoyu [1 ]
Zhang, Hanyu [1 ]
Wang, Guanjie [2 ]
机构
[1] ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
[2] Shanghai Lixin Univ Accounting & Finance, Sch Stat & Math, Shanghai 201209, Peoples R China
关键词
Bayesian inverse problem; uncertainty quantification; ANOVA decomposition; principle component analysis; Gaussian process regression; GAUSSIAN-PROCESSES; REDUCTION; PARAMETER;
D O I
10.3390/math12020301
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Markov chain Monte Carlo (MCMC) stands out as an effective method for tackling Bayesian inverse problems. However, when dealing with computationally expensive forward models and high-dimensional parameter spaces, the challenge of repeated sampling becomes pronounced. A common strategy to address this challenge is to construct an inexpensive surrogate of the forward model, which cuts the computational cost of individual samples. While the Gaussian process (GP) is widely used as a surrogate modeling strategy, its applicability can be limited when dealing with high-dimensional input or output spaces. This paper presents a novel approach that combines the analysis of variance (ANOVA) decomposition method with Gaussian process regression to handle high-dimensional Bayesian inverse problems. Initially, the ANOVA method is employed to reduce the dimension of the parameter space, which decomposes the original high-dimensional problem into several low-dimensional sub-problems. Subsequently, principal component analysis (PCA) is utilized to reduce the dimension of the output space on each sub-problem. Finally, a Gaussian process model with a low-dimensional input and output is constructed for each sub-problem. In addition to this methodology, an adaptive ANOVA-GP-MCMC algorithm is proposed, which further enhances the adaptability and efficiency of the method in the Bayesian inversion setting. The accuracy and computational efficiency of the proposed approach are validated through numerical experiments. This innovative integration of ANOVA and Gaussian processes provides a promising solution to address challenges associated with high-dimensional parameter spaces and computationally expensive forward models in Bayesian inference.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] An adaptive ANOVA-based PCKF for high-dimensional nonlinear inverse modeling
    Li, Weixuan
    Lin, Guang
    Zhang, Dongxiao
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2014, 258 : 752 - 772
  • [2] Sparse Bayesian hierarchical modeling of high-dimensional clustering problems
    Lian, Heng
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2010, 101 (07) : 1728 - 1737
  • [3] Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
    Xia, Yingzhi
    Zabaras, Nicholas
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2022, 455
  • [4] Multimodal, high-dimensional, model-based, Bayesian inverse problems with applications in biomechanics
    Franck, I. M.
    Koutsourelakis, P. S.
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2017, 329 : 91 - 125
  • [5] An adaptive reduced basis ANOVA method forhigh-dimensional Bayesian inverse problems
    Liao, Qifeng
    Li, Jinglai
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2019, 396 : 364 - 380
  • [6] Fast Bayesian inversion for high dimensional inverse problems
    Kugler, Benoit
    Forbes, Florence
    Doute, Sylvain
    [J]. STATISTICS AND COMPUTING, 2022, 32 (02)
  • [7] Fast Bayesian inversion for high dimensional inverse problems
    Benoit Kugler
    Florence Forbes
    Sylvain Douté
    [J]. Statistics and Computing, 2022, 32
  • [8] One-Way High-Dimensional ANOVA
    Chen, Tansheng
    Zheng, Lukun
    [J]. JOURNAL OF MATHEMATICS, 2023, 2023
  • [9] A BAYESIAN LINEAR MODEL FOR THE HIGH-DIMENSIONAL INVERSE PROBLEM OF SEISMIC TOMOGRAPHY
    Zhang, Ran
    Czado, Claudia
    Sigloch, Karin
    [J]. ANNALS OF APPLIED STATISTICS, 2013, 7 (02): : 1111 - 1138
  • [10] Variational Bayesian strategies for high-dimensional, stochastic design problems
    Koutsourelakis, P. S.
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2016, 308 : 124 - 152