Learning Latent Permutations with Gumbel-Sinkhorn Networks

@article{Mena2018LearningLP,
  title={Learning Latent Permutations with Gumbel-Sinkhorn Networks},
  author={Gonzalo E. Mena and David Belanger and Scott W. Linderman and Jasper Snoek},
  journal={CoRR},
  year={2018},
  volume={abs/1802.08665}
}
Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn operator is attractive… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 21 times over the past 90 days. VIEW TWEETS

Similar Papers

Loading similar papers…