google-deepmind/kfac-jax

Second Order Optimization and Curvature Estimation with K-FAC in JAX.

60
/ 100
Established

This tool helps machine learning researchers efficiently train neural networks. It takes a neural network definition and training data, then applies advanced optimization techniques to speed up the learning process. The output is a more quickly and effectively trained model. Researchers working with neural networks, especially those focused on deep learning, will find this beneficial for their experimentation and model development.

317 stars. Available on PyPI.

Use this if you are a machine learning researcher training neural networks and want to leverage second-order optimization methods for faster and more stable convergence.

Not ideal if you are looking for a general-purpose, high-level machine learning framework and are not comfortable with lower-level JAX-based neural network implementation details.

deep-learning neural-network-training machine-learning-research model-optimization
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

317

Forks

29

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-deepmind/kfac-jax"

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