期刊
FRONTIERS IN PHYSICS
卷 10, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fphy.2022.1058809
关键词
bayesian inference; probability updates; importance resampling; uncertainty quantification; ab initio nuclear theory; low-energy constants
资金
- European Research Council under the European Union [758027]
- Swedish Research Council [2017-04234, 2021-04507, 2018-05973]
- Swedish Research Council [2021-04507, 2017-04234] Funding Source: Swedish Research Council
- European Research Council (ERC) [758027] Funding Source: European Research Council (ERC)
We introduce a Bayesian sampling method called sampling/importance resampling and discuss its specific usefulness in nuclear theory. By analyzing a toy problem and presenting realistic applications, we demonstrate the method's effectiveness in inferring posterior distributions and estimating posterior probability distributions. However, we also highlight the limitations of the method in extreme situations where it breaks.
We review an established Bayesian sampling method called sampling/importance resampling and highlight situations in nuclear theory when it can be particularly useful. To this end we both analyse a toy problem and demonstrate realistic applications of importance resampling to infer the posterior distribution for parameters of delta NNLO interaction model based on chiral effective field theory and to estimate the posterior probability distribution of target observables. The limitation of the method is also showcased in extreme situations where importance resampling breaks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据