Bayesian model inversion using stochastic spectral embedding
Journal of Computational Physics(2021)
摘要
•We present the SSLE approach for Bayesian model inversion based on SSE and SLE.•Posterior quantities are obtained analytically from the SSLE coefficients.•The original SSE algorithm is enhanced with an active learning enrichment scheme.•This method generalizes and drastically improves the efficiency of the SLE approach.•We showcase the method on three problems of different complexity and dimensionality.
更多查看译文
关键词
Bayesian model inversion,Inverse problems,Polynomial chaos expansions,Spectral likelihood expansions,Stochastic spectral likelihood embedding,Sampling-free inversion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络