kenziyuliu/DP2

[ICLR 2023] Official JAX/Haiku implementation of the paper "Differentially Private Adaptive Optimization with Delayed Preconditioners"

22
/ 100
Experimental

This project helps machine learning researchers and practitioners develop and train models while ensuring user data privacy. It takes your dataset and model architecture as input, applying specialized optimization techniques to produce a trained model that balances high performance with strong privacy guarantees. Researchers focused on privacy-preserving machine learning will find this particularly useful.

No commits in the last 6 months.

Use this if you need to train machine learning models on sensitive data and want to achieve better model accuracy while strictly adhering to differential privacy standards.

Not ideal if your primary goal is model training without privacy constraints, or if you are looking for a plug-and-play solution without understanding privacy-preserving optimization methods.

privacy-preserving machine learning secure model training differential privacy adaptive optimization privacy research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

Apache-2.0

Last pushed

Dec 14, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kenziyuliu/DP2"

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