namkoong-lab/dro

A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch

55
/ 100
Established

This package helps machine learning practitioners build more reliable predictive models, especially when real-world data might differ slightly from training data. You input your labeled datasets (features and target labels) for tasks like classification or regression. The output is a robust model that's less sensitive to unexpected variations in future data. This is for data scientists, machine learning engineers, and researchers who develop and deploy predictive models.

157 stars. Available on PyPI.

Use this if you need to develop machine learning models (like SVM, logistic, or linear regression) that are resilient to potential shifts or uncertainties in your data distribution.

Not ideal if you are looking for a general-purpose machine learning library for deep learning or complex, non-linear models outside of distributionally robust optimization.

predictive-modeling machine-learning-robustness data-uncertainty statistical-modeling model-reliability
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 10 / 25

How are scores calculated?

Stars

157

Forks

10

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 08, 2026

Commits (30d)

0

Dependencies

13

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/namkoong-lab/dro"

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