activatedgeek/tight-pac-bayes

Code for PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization, NeurIPS 2022

37
/ 100
Emerging

This project helps machine learning researchers understand why deep neural networks generalize well, even with many parameters. It takes trained deep learning models and datasets as input and outputs a 'tight PAC-Bayes compression bound,' which is a theoretical measure explaining how much information is truly needed for the model to perform its task. Researchers working in machine learning theory, especially those focused on generalization and model compression, would use this tool.

No commits in the last 6 months.

Use this if you are a machine learning researcher trying to theoretically explain the generalization capabilities of deep neural networks by quantifying their effective complexity.

Not ideal if you are looking for a practical tool to reduce the size of your models for deployment or to improve their empirical performance.

machine-learning-theory neural-network-generalization model-compression-theory information-theory statistical-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

19

Forks

5

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 23, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/activatedgeek/tight-pac-bayes"

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