activatedgeek/tight-pac-bayes
Code for PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization, NeurIPS 2022
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.
Stars
19
Forks
5
Language
Jupyter Notebook
License
Apache-2.0
Category
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.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)