neuralsbi: Neural Simulation-Based Inference
A native R implementation of neural simulation-based inference, focused on Neural Posterior Estimation. Given a prior over parameters and a simulator, 'neuralsbi' trains a conditional neural density estimator to approximate the Bayesian posterior, enabling amortized, likelihood-free inference. Neural estimators run on the 'torch' back end. It targets applied researchers who want an approachable interface with sensible defaults and built-in posterior diagnostics.
| Version: | 0.3.2 |
| Depends: | R (≥ 4.1.0) |
| Imports: | stats, utils |
| Suggests: | torch (≥ 0.11.0), testthat (≥ 3.0.0), knitr, rmarkdown |
| Published: | 2026-08-03 |
| DOI: | 10.32614/CRAN.package.neuralsbi (may not be active yet) |
| Author: | Pedro Nascimento de Lima
 [aut, cre] |
| Maintainer: | Pedro Nascimento de Lima <plima at rand.org> |
| BugReports: | https://github.com/pedroliman/neuralsbi/issues |
| License: | MIT + file LICENSE |
| URL: | https://pedroliman.github.io/neuralsbi/, https://github.com/pedroliman/neuralsbi |
| NeedsCompilation: | no |
| Materials: | README, NEWS |
| CRAN checks: | neuralsbi results |
Documentation:
| Reference manual: | neuralsbi.html , neuralsbi.pdf |
| Vignettes: |
Choosing a density estimator (source) Checking the posterior (source) Getting started with neuralsbi (source) Case study: inferring epidemic parameters (SIR) (source) |
Downloads:
| Package source: | neuralsbi_0.3.2.tar.gz |
| Windows binaries: | r-devel: neuralsbi_0.3.2.zip, r-release: not available, r-oldrel: neuralsbi_0.3.2.zip |
| macOS binaries: | r-release (arm64): neuralsbi_0.3.2.tgz, r-oldrel (arm64): neuralsbi_0.3.2.tgz, r-release (x86_64): neuralsbi_0.3.2.tgz, r-oldrel (x86_64): neuralsbi_0.3.2.tgz |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=neuralsbi to link to this page.