google-deepmind / kfac-jax
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
Why this job: matched by what the repo talks about: second, optimization
What it does
KFAC-JAX is a library built on top of [JAX] for second-order optimization of neural networks and for computing scalable curvature approximations. The main goal of the library is to provide researchers with an easy-to-use implementation of the [K-FAC] optimizer and curvature estimator.
Get started
$ pip install git+https://github.com/google-deepmind/kfac-jax - Maintenance
- Active
- Last commit 34 days ago
- Stars
- 332
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.0.8
- Released 8 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 56% closed
- 11 still open
- Pull requests
- 219 merged
- 12 waiting
- Releases
- 7
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 100%
- Shell <1%
Topics
- machine-learning
- optimization
- bayesian-deep-learning
Project record
- JobNotes and knowledge
- StatusListed
- Commits371
- Forks33
- Watching11
- Stars in 28 days+1
- CreatedMar 18, 2022
- First seen by usNov 7, 2026
- CheckedNov 8, 2026