Continuous Mixtures of Tractable Probabilistic Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Correia, Alvaro H. C., Gala, Gennaro, Quaeghebeur, Erik, de Campos, Cassio, Peharz, Robert
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911932631482368
author Correia, Alvaro H. C.
Gala, Gennaro
Quaeghebeur, Erik
de Campos, Cassio
Peharz, Robert
author_facet Correia, Alvaro H. C.
Gala, Gennaro
Quaeghebeur, Erik
de Campos, Cassio
Peharz, Robert
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2209_10584
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Continuous Mixtures of Tractable Probabilistic Models
Correia, Alvaro H. C.
Gala, Gennaro
Quaeghebeur, Erik
de Campos, Cassio
Peharz, Robert
Machine Learning
Artificial Intelligence
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.
title Continuous Mixtures of Tractable Probabilistic Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2209.10584