Skip to yearly menu bar Skip to main content


Differentiable Random Partition Models

Thomas Sutter · Alain Ryser · Joram Liebeskind · Julia Vogt

Great Hall & Hall B1+B2 (level 1) #1015
[ ] [ Project Page ]
[ Paper [ Poster [ OpenReview
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST


Partitioning a set of elements into an unknown number of mutually exclusive subsets is essential in many machine learning problems.However, assigning elements, such as samples in a dataset or neurons in a network layer, to an unknown and discrete number of subsets is inherently non-differentiable, prohibiting end-to-end gradient-based optimization of parameters.We overcome this limitation by proposing a novel two-step method for inferring partitions, which allows its usage in variational inference tasks.This new approach enables reparameterized gradients with respect to the parameters of the new random partition model.Our method works by inferring the number of elements per subset and, second, by filling these subsets in a learned order.We highlight the versatility of our general-purpose approach on three different challenging experiments: variational clustering, inference of shared and independent generative factors under weak supervision, and multitask learning.

Chat is not available.