Software

An initial list of SBI-related software packages

SBI (python) - general purpose SBI framework
SBI Benchmarking (python) - for benchmarking
MadMiner - aimed at particle physics
swyft (python) the reference implementation of Truncated Marginal Neural Ratio Estimation (TMNRE), an efficient, simulation-based inference technique for complex data and expensive simulators
carl an early NN-based SBI package
lampe (python) is a flexible, amortized sbi library. The philosophy of LAMPE is to avoid obfuscation and expose all components so it is most useful for researchers.
pydelfi (python) with neural density estimators and adaptive acquisition of simulations.

Latest Posts

Marginal Flow a flexible and efficient framework for density estimation

MM Negri, J Aellen, M Jahn… - arXiv preprint arXiv …, 2025 - arxiv.org

… Figure 14: Simulation-based inference benchmark: we show average and standard deviation over 10 different test observations. We compare our method against Free-…

One-shot Conditional Sampling MMD meets Nearest Neighbors

A Chatterjee, S Choudhury, R Hore - arXiv preprint arXiv:2509.25507, 2025 - arxiv.org

… both modern machine learning and classical statistics, including image post-processing in computer vision, approximate posterior sampling in simulation-based inference, …

Flow Matching for Robust Simulation-Based Inference under Model Misspecification

PL Ruhlmann, PLC Rodrigues, M Arbel… - arXiv preprint arXiv …, 2025 - arxiv.org

Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simulated data. A persistent …

Simulation-Based Inference of Cell Migration Dynamics in Complex Spatial Environments

J Arruda, E Alamoudi, R Mueller, M Vaisband… - bioRxiv, 2025 - biorxiv.org

… , we demonstrate that the learned summaries exhibit 354 superior performance compared to traditional summary statistics in the context of 355 simulation-based inference. …