adrienkegreisz/ano-optimizer

Lightweight and customizable optimizer compatible with PyTorch and TensorFlow.

22
/ 100
Experimental

This project offers a specialized optimizer for training machine learning models, particularly when dealing with noisy or high-variance data. It takes your model's parameters and gradients, then applies an optimized update strategy to help the model learn more efficiently and stably. Data scientists and machine learning engineers who develop and train deep learning models will find this useful for improving convergence.

No commits in the last 6 months.

Use this if you are training deep learning models in PyTorch or TensorFlow and encounter challenges with training stability or slow convergence due to noisy gradients or high-variance data.

Not ideal if your models are small, training on clean, low-variance datasets, or if you are not working with deep learning frameworks like PyTorch or TensorFlow.

machine-learning-engineering deep-learning-training model-optimization neural-networks data-science
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MIT

Last pushed

Jul 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adrienkegreisz/ano-optimizer"

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