montefiore-institute/balanced-nre

Code for the paper "Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation".

31
/ 100
Emerging

This project helps scientists and researchers who use complex computer simulations to understand real-world phenomena. It takes your simulation outputs and helps you infer the underlying parameters that produced them, providing more reliable and less overconfident results. This is for anyone who needs to be sure their conclusions from simulation-based models are robust, without risking false inferences due to overly optimistic predictions.

No commits in the last 6 months.

Use this if you conduct simulation-based inference and need to ensure your estimated posteriors are conservative and trustworthy, especially when dealing with limited simulation data.

Not ideal if your primary goal is to maximize computational speed at the cost of potential overconfidence in your simulation-based inference results.

simulation-based inference scientific modeling computational science statistical inference parameter estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

14

Forks

2

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Nov 14, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/montefiore-institute/balanced-nre"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.