milenagazdieva/U-NOTBarycenters

PyTorch implementation of "Robust Barycenter Estimation using Semi-unbalanced Neural Optimal Transport" (ICLR 2025)

29
/ 100
Experimental

This project helps researchers and data scientists working with complex data distributions to find a meaningful 'average' representation, called a barycenter. You input several high-dimensional data distributions, potentially containing outliers or class imbalances, and it outputs a single, robust barycenter that accurately reflects the core characteristics of the input data while ignoring noise. It's designed for quantitative researchers, machine learning practitioners, or data analysts dealing with statistical comparisons or generative modeling tasks.

No commits in the last 6 months.

Use this if you need to compute a robust average (barycenter) of multiple data distributions, especially when these distributions might contain noisy data points or have unequal sample sizes.

Not ideal if you are looking for a simple average calculation or if your distributions are low-dimensional and guaranteed to be clean without outliers or imbalances.

data-distribution-analysis statistical-modeling machine-learning-research generative-modeling data-robustness
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/milenagazdieva/U-NOTBarycenters"

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