google-deepmind/kfac-jax
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
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.
Stars
317
Forks
29
Language
Python
License
Apache-2.0
Category
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.
Related frameworks
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/