f-EBM

Code for Training Deep Energy-Based Models with f-Divergence Minimization.

Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon. Stanford AI Lab.

The 37th International Conference on Machine Learning.

The code for the simple 1-D example can be found here and the code for image generation can be found here.

References

If you find this work useful in your research, please consider citing the following paper:

@article{yu2020training,
  title={Training Deep Energy-Based Models with f-Divergence Minimization},
  author={Yu, Lantao and Song, Yang and Song, Jiaming and Ermon, Stefano},
  journal={arXiv preprint arXiv:2003.03463},
  year={2020}
}