machinestein/General-Cost-Neural-Optimal-Transport

Official Pytorch implementation of "Neural Optimal Transport with General Cost Functionals" (ICLR 2024)

18
/ 100
Experimental

This project helps researchers and practitioners in machine learning and data science who need to transform data distributions from one form to another while minimizing a specific 'cost' or 'effort' for that transformation. It takes in two data distributions and a custom cost function, then outputs a neural network that maps one distribution to the other efficiently. This is ideal for scientists working with complex datasets where traditional data alignment methods fall short.

No commits in the last 6 months.

Use this if you need to align or translate complex data distributions (like images or biological data) based on a custom, high-dimensional cost function that reflects the specific transformation you want.

Not ideal if your data transformations are simple, low-dimensional, or if you don't need to define a custom, complex cost function for the transport.

data-alignment image-to-image-translation batch-effect-correction distribution-matching data-transformation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

24

Forks

1

Language

Jupyter Notebook

License

Last pushed

Aug 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/machinestein/General-Cost-Neural-Optimal-Transport"

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