EmanuelSommer/MILE

Code for the ICLR 2025 paper: "Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks"

/ 100

Emerging

This project helps machine learning practitioners more efficiently train Bayesian Neural Networks (BNNs). It takes your BNN configuration and data, then generates high-quality posterior samples and model diagnostics faster than traditional methods. The output includes trained models, posterior samples, performance metrics, and visualizations, enabling quicker development and evaluation of robust models.

No commits in the last 6 months.

Use this if you need to sample Bayesian Neural Networks and want to significantly reduce the time it takes to get high-quality results compared to existing methods like NUTS.

Not ideal if you are working with non-Bayesian neural networks or if your primary goal is not efficient sampling for uncertainty quantification.

Bayesian-modeling machine-learning-engineering predictive-analytics uncertainty-quantification model-training

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 4 / 25

Maturity 16 / 25

Community 15 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

MIT

Higher-rated alternatives

sbi-dev/sbi

sbi is a Python package for simulation-based inference, designed to meet the needs of both...

SMTorg/smt

Surrogate Modeling Toolbox

reservoirpy/reservoirpy

A simple and flexible code for Reservoir Computing architectures like Echo State Networks

GPflow/GPflow

Gaussian processes in TensorFlow

dswah/pyGAM

[CONTRIBUTORS WELCOME] Generalized Additive Models in Python

Explore ML Frameworks

All categories Trending ML Framework directory Insights