An adaptive Gaussian process method for multi-modal Bayesian inverse problems
2024-09-05
状态已发表
摘要Inverse problems are prevalent in both scientific research and engineering applications. In the context of Bayesian inverse problems, sampling from the posterior distribution is particularly challenging when the forward models are computationally expensive. This challenge escalates further when the posterior distribution is multimodal. To address this, we propose a Gaussian process (GP) based method to indirectly build surrogates for the forward model. Specifically, the unnormalized posterior density is expressed as a product of an auxiliary density and an exponential GP surrogate. In an iterative way, the auxiliary density will converge to the posterior distribution starting from an arbitrary initial density. However, the e ffi ciency of the GP regression is highly influenced by the quality of the training data. Therefore, we utilize the iterative local updating ensemble smoother (ILUES) to generate high-quality samples that are concentrated in regions with high posterior probability. Subsequently, based on the surrogate model and the mode information that is extracted by using a clustering method, MCMC with a Gaussian mixed (GM) proposal is used to draw samples from the auxiliary density. Through numerical examples, we demonstrate that the proposed method can accurately and e ffi ciently represent the posterior with a limited number of forward simulations.
关键词Bayesian inverse problems Multimodal Gaussian process Surrogate ILUES
语种英语
DOIarXiv:2409.15307
相关网址查看原文
出处Arxiv
收录类别PPRN.PPRN
WOS记录号PPRN:98863926
WOS类目Computer Science, Interdisciplinary Applications ; Statistics& Probability
文献类型预印本
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/433542
专题信息科学与技术学院
信息科学与技术学院_PI研究组_廖奇峰组
信息科学与技术学院_硕士生
通讯作者Liao, Qifeng
作者单位
1.Univ Houston, Dept Math, Houston, TX 77204, USA
2.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
3.Calif State Univ, Dept Informat Syst & Decis Sci, Fullerton, CA 92831, USA
推荐引用方式
GB/T 7714
Xu, Zhihang,Zhu, Xiaoyu,Li, Daoji,et al. An adaptive Gaussian process method for multi-modal Bayesian inverse problems. 2024.
条目包含的文件
条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Xu, Zhihang]的文章
[Zhu, Xiaoyu]的文章
[Li, Daoji]的文章
百度学术
百度学术中相似的文章
[Xu, Zhihang]的文章
[Zhu, Xiaoyu]的文章
[Li, Daoji]的文章
必应学术
必应学术中相似的文章
[Xu, Zhihang]的文章
[Zhu, Xiaoyu]的文章
[Li, Daoji]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。