Options
Inversion of Bayesian networks
Citation Link: https://doi.org/10.15480/882.8848
Publikationstyp
Journal Article
Date Issued
2023-10-16
Sprache
English
TORE-DOI
Volume
164
Article Number
109042
Citation
International Journal of Approximate Reasoning 164 : 109042 (2024)
Publisher DOI
Scopus ID
Publisher
Elsevier
Variational autoencoders and Helmholtz machines use a recognition network (encoder) to approximate the posterior distribution of a generative model (decoder). In this paper we establish some necessary and some sufficient properties of a recognition network so that it can model the true posterior distribution exactly. These results are derived in the general context of probabilistic graphical modelling / Bayesian networks, for which the network represents a set of conditional independence statements. We derive both global conditions, in terms of d-separation, and local conditions for the recognition network to have the desired qualities. It turns out that for the local conditions the perfectness property (for every node, all parents are joined) plays an important role.
Subjects
Amortized inference
Bayesian networks
Generative model
Graphical models
Recognition model
Variational autoencoder
Variational inference
DDC Class
004: Computer Sciences
Publication version
publishedVersion
Loading...
Name
1-s2.0-S0888613X23001731-main.pdf
Type
Main Article
Size
588.72 KB
Format
Adobe PDF