Papers

An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning

M Dax, T Heimel, G Louppe - arXiv preprint arXiv:2607.21702, 2026 - arxiv.org
Computer Science paper cs.LG Suggest

… learning techniques for simulation-based inference (Sec. 3… literature on simulation-based inference applications, we … examples for applying simulation-based inference. …

Link to paper

BibTeX

@article{2607.21702v1,
Author        = {Maximilian Dax and Theo Heimel and Gilles Louppe},
Title         = {An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning},
Eprint        = {2607.21702v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.LG},
Abstract      = {Simulation-based inference (SBI) with machine learning is an increasingly important tool for solving inverse problems in science and engineering, including parameter inference and the inversion of detector effects. We provide an overview of the Bayesian and frequentist statistical frameworks, describe how machine-learning-based SBI methods, such as neural posterior estimation and neural likelihood estimation, can be used for parameter estimation within these frameworks, and show that the same methods can also be applied to Empirical Bayes or unfolding tasks. We also discuss how to validate inference results and the limitations of SBI with machine learning.},
Year          = {2026},
Month         = {Jul},
Url           = {http://arxiv.org/abs/2607.21702v1},
File          = {2607.21702v1.pdf}
}

Share