pmichel31415/P-DRO

Code for the papers "Modeling the Second Player in Distributionally Robust Optimization" and "Distributionally Robust Models with Parametric Likelihood Ratios"

32
/ 100
Emerging

This tool helps machine learning engineers and researchers build more reliable classification models, especially for natural language processing tasks like sentiment analysis. It takes a dataset for classification and outputs a model that performs robustly even when there are shifts or biases in the data distribution. The main user would be someone developing and deploying AI models where fairness or generalization across varied real-world data is critical.

No commits in the last 6 months.

Use this if you need to train a classification model that is resilient to potential distribution shifts in your real-world data, ensuring consistent performance across different data subsets or biases.

Not ideal if you are looking for a simple, off-the-shelf classification model without needing to delve into advanced robust optimization techniques or fine-tune adversary models.

natural-language-processing robust-ai machine-learning-engineering model-reliability sentiment-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

29

Forks

8

Language

Python

License

Last pushed

Apr 14, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pmichel31415/P-DRO"

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