Wasserstein Training of Restricted Boltzmann Machines

@inproceedings{Montavon2016WassersteinTO,
  title={Wasserstein Training of Restricted Boltzmann Machines},
  author={Gr{\'e}goire Montavon and Klaus-Robert M{\"u}ller and Marco Cuturi},
  booktitle={NIPS},
  year={2016}
}
Boltzmann machines are able to learn highly complex, multimodal, structured and multiscale real-world data distributions. Parameters of the model are usually learned by minimizing the Kullback-Leibler (KL) divergence from training samples to the learned model. We propose in this work a novel approach for Boltzmann machine training which assumes that a meaningful metric between observations is known. This metric between observations can then be used to define the Wasserstein distance between the… CONTINUE READING
Highly Cited
This paper has 38 citations. REVIEW CITATIONS

References

Publications referenced by this paper.