33 citations · 74 across the 5 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2018
Learning Latent Permutations with Gumbel-Sinkhorn Networks
Gonzalo Mena, David Belanger, Scott Linderman +1
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 diffi…
stat.ML2015★ 12 cited
A Linear Dynamical System Model for Text
David Belanger, Sham Kakade
Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words' local context, a natural way to…