Continuous Mixtures of Tractable Probabilistic Models

Alvaro H.C. Correia*, Gennaro Gala, Erik Quaeghebeur, Cassio de Campos, Robert Peharz

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

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.

Originalspracheenglisch
TitelProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
UntertitelAAAI-23 Technical Tracks 6
Redakteure/-innenBrian Williams, Yiling Chen, Jennifer Neville
Herausgeber (Verlag)AAAI Press
Seiten7244-7252
Seitenumfang9
ISBN (elektronisch)9781577358800
PublikationsstatusVeröffentlicht - 27 Juni 2023
Veranstaltung37th AAAI Conference on Artificial Intelligence: AAAI 2023 - Washington DC, USA / Vereinigte Staaten
Dauer: 7 Feb. 202314 Feb. 2023
https://aaai-23.aaai.org
https://aaai.org/Conferences/AAAI-23/

Konferenz

Konferenz37th AAAI Conference on Artificial Intelligence
KurztitelAAAI 2023
Land/GebietUSA / Vereinigte Staaten
OrtWashington DC
Zeitraum7/02/2314/02/23
Internetadresse

ASJC Scopus subject areas

  • Artificial intelligence

Fingerprint

Untersuchen Sie die Forschungsthemen von „Continuous Mixtures of Tractable Probabilistic Models“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren