ysngshn/ivon-optax

An Optax-based JAX implementation of the IVON optimizer for large-scale VI training of NNs (ICML'24 spotlight)

21
/ 100
Experimental

This tool helps machine learning engineers and researchers train large neural networks more effectively, especially when dealing with uncertainty. It takes your neural network model and training data, and outputs a more robustly trained model with improved accuracy and better estimations of prediction uncertainty. This is particularly useful for those working with cutting-edge deep learning models and Bayesian inference techniques.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher looking to improve the training stability and performance of large neural networks, especially when using variational inference.

Not ideal if you are a beginner in machine learning or primarily work with PyTorch, as this implementation is specifically for JAX and requires familiarity with its ecosystem.

deep-learning neural-networks variational-inference model-training bayesian-deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

GPL-3.0

Last pushed

Dec 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ysngshn/ivon-optax"

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