Abstract
Probabilistic models based on continuous latent spaces, such as variational autoencoders, can be understood as uncountable mixture models where components depend continuously on the latent code. They have proven to be expressive tools for generative and probabilistic modelling, but are at odds with tractable probabilistic inference, that is, computing marginals and conditionals of the represented probability distribution. Meanwhile, tractable probabilistic models such as probabilistic circuits (PCs) can be understood as hierarchical discrete mixture models, and thus are capable of performing exact inference efficiently but often show subpar performance in comparison to continuous latent-space models. In this paper, we investigate a hybrid approach, namely continuous mixtures of tractable models with a small latent dimension. While these models are analytically intractable, they are well amenable to numerical integration schemes based on a finite set of integration points. With a large enough number of integration points the approximation becomes de-facto exact. Moreover, for a finite set of integration points, the integration method effectively compiles the continuous mixture into a standard PC. In experiments, we show that this simple scheme proves remarkably effective, as PCs learnt this way set new state of the art for tractable models on many standard density estimation benchmarks.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023 |
| Subtitle of host publication | AAAI-23 Technical Tracks 6 |
| Editors | Brian Williams, Yiling Chen, Jennifer Neville |
| Publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
| Pages | 7244-7252 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781577358800 |
| Publication status | Published - 27 Jun 2023 |
| Event | 37th AAAI Conference on Artificial Intelligence: AAAI 2023 - Washington DC, United States Duration: 7 Feb 2023 → 14 Feb 2023 https://aaai-23.aaai.org https://aaai.org/Conferences/AAAI-23/ |
Conference
| Conference | 37th AAAI Conference on Artificial Intelligence |
|---|---|
| Abbreviated title | AAAI 2023 |
| Country/Territory | United States |
| City | Washington DC |
| Period | 7/02/23 → 14/02/23 |
| Internet address |
ASJC Scopus subject areas
- Artificial Intelligence
Fields of Expertise
- Information, Communication & Computing
Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS