Neural Permutation Processes

Ari Pakman, Yueqi Wang, Liam Paninski

Research output: Contribution to journalConference articlepeer-review


We introduce a neural architecture to perform amortized approximate Bayesian inference over latent random permutations of two sets of objects. The method involves approximating permanents of matrices of pairwise probabilities using recent ideas on functions defined over sets. Each sampled permutation comes with a probability estimate, a quantity unavailable in MCMC approaches. We illustrate the method in sets of 2D points and MNIST images.

Original languageEnglish
JournalProceedings of Machine Learning Research
StatePublished - 1 Jan 2019
Externally publishedYes
Event2nd Symposium on Advances in Approximate Bayesian Inference, AABI 2019 - Vancouver, Canada
Duration: 8 Dec 2019 → …

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Neural Permutation Processes'. Together they form a unique fingerprint.

Cite this