atomicarchitects/PriceofFreedom

[ICML'25] The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products

21
/ 100
Experimental

This project helps machine learning researchers explore the balance between how complex an AI model can be and how fast it runs. It takes as input various configurations of 'equivariant tensor products'—a specific type of mathematical operation in AI—and outputs measurements of their expressivity (power) and computational efficiency (speed). It's designed for researchers developing or evaluating advanced machine learning models, especially those in areas like physics-informed AI or geometric deep learning.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner who needs to understand the performance tradeoffs of different equivariant neural network architectures.

Not ideal if you are looking for a general-purpose machine learning library for standard data analysis or an end-user application.

machine-learning-research equivariant-neural-networks computational-efficiency model-expressivity AI-architecture-design
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Jupyter Notebook

License

Last pushed

Jul 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/atomicarchitects/PriceofFreedom"

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