Open access
Date
2024-07Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000648756Publication status
publishedExternal links
Book title
Advances in Neural Information Processing Systems 36Pages / Article No.
Publisher
CurranEvent
Organisational unit
09670 - Vogt, Julia / Vogt, Julia
Related publications and datasets
Is new version of: https://doi.org/10.48550/arXiv.2305.16841
Notes
Poster presentation on December 12, 2023.More
Show all metadata
ETH Bibliography
yes
Altmetrics