BriefGPT.xyz
Feb, 2018
使用Gumbel-Sinkhorn网络学习潜在的置换
Learning Latent Permutations with Gumbel-Sinkhorn Networks
HTML
PDF
Gonzalo Mena, David Belanger, Scott Linderman, Jasper Snoek
TL;DR
介绍了一系列以连续Sinkhorn运算符来近似离散最大权匹配的新方法，应用在排序数字，拼图和鉴别神经信号等任务中，并且在竞争基线上取得了更好的效果。
Abstract
permutations
and
matchings
are core building blocks in a variety of
latent variable models
, as they allow us to align, canonicalize, and s
→