/CV-SW

Official PyTorch implementation for paper: Sliced Wasserstein Estimation with Control Variates

Primary LanguagePythonMIT LicenseMIT

CV-SW

Official PyTorch implementation for paper: Sliced Wasserstein Estimation with Control Variates

Details of the model architecture and experimental results can be found in our papers.

@article{nguyen2024control,
  title={Sliced Wasserstein Estimation with Control Variates},
  author={Khai Nguyen and Nhat Ho},
  booktitle={International Conference on Learning Representations},
  year={2024},
  pdf={https://arxiv.org/pdf/2305.00402.pdf}
}

Please CITE our paper whenever this repository is used to help produce published results or incorporated into other software.

This implementation is made by Khai Nguyen.

Requirements

To install the required python packages, run

pip install -r requirements.txt

What is included?

  • Point-Cloud Gradient flow
  • Generative model

Point-Cloud Gradient flow

cd GradientFlow
python main_point.py

Generative Model

Please read the README file in the Generative_model folder.