jaepil/geometric-adam

A Ray Tracing-Inspired Approach to Neural Network Optimization

23
/ 100
Experimental

This optimization algorithm helps machine learning engineers train large neural network models more reliably. It takes your model's parameters and trains them with an innovative 'ray tracing' approach, preventing common training failures and producing a more accurate, stable model. It's designed for machine learning researchers and engineers who work with deep learning models, especially large transformers, who struggle with models diverging during long training runs.

No commits in the last 6 months.

Use this if your large neural network models frequently diverge or fail during training, and you need a more stable and robust way to achieve high performance over many training epochs.

Not ideal if you are looking for a fully production-ready, off-the-shelf solution, as this project is an active research exploration rather than a finished product.

neural-network-training deep-learning-optimization transformer-models model-stability machine-learning-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

17

Forks

Language

Python

License

MIT

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jaepil/geometric-adam"

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