ysngshn/ivon-optax
An Optax-based JAX implementation of the IVON optimizer for large-scale VI training of NNs (ICML'24 spotlight)
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.
Stars
9
Forks
—
Language
Python
License
GPL-3.0
Category
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.
Higher-rated alternatives
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/