Conference item
BRUNO: A deep recurrent model for exchangeable data
- Abstract:
- We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations. Our model is provably exchangeable, meaning that the joint distribution over observations is invariant under permutation: this property lies at the heart of Bayesian inference. The model does not require variational approximations to train, and new samples can be generated conditional on previous samples, with cost linear in the size of the conditioning set. The advantages of our architecture are demonstrated on learning tasks that require generalisation from short observed sequences while modelling sequence variability, such as conditional image generation, few-shot learning, and anomaly detection.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
- Publisher:
- Massachusetts Institute of Technology Press
- Host title:
- Advances in Neural Information Processing Systems
- Journal:
- Advances in Neural Information Processing Systems More from this journal
- Publication date:
- 2018-12-01
- Acceptance date:
- 2018-09-05
- Event location:
- Montreal
- ISSN:
-
1049-5258
- Pubs id:
-
pubs:1045797
- UUID:
-
uuid:b742c28e-9f2a-4b5a-926c-f512306fa5c6
- Local pid:
-
pubs:1045797
- Source identifiers:
-
1045797
- Deposit date:
-
2019-08-16
Terms of use
- Copyright holder:
- Neural Information Processing Systems Foundation
- Copyright date:
- 2018
- Notes:
- © 2018 Neural Information Processing Systems Foundation, Inc. This paper has been presented at the Thirty-second Conference on Neural Information Processing Systems (NIPS 2018). It is available at: https://papers.nips.cc/paper/7949-bruno-a-deep-recurrent-model-for-exchangeable-data.pdf
If you are the owner of this record, you can report an update to it here: Report update to this record