back to list

Project: Hybrid Bayesian networks

Description

This internal project aims at developing and testing (for example in classification tasks) a generative model based on probabilistic graphical models for domains with continuous and categorical variables. We want to learn both the graph structure and parameters of such models while constraining their complexity (for instance as measured by the tree-width of the graph). Moreover, we may try to create a structural expectation-maximisation approach so that we can deal with latent variables. We may start with simple graph types and expand to more complex models.

References:

https://arxiv.org/abs/2306.06517

https://arxiv.org/abs/1406.1411v1

https://arxiv.org/abs/1605.03392

Details

Supervisor

Cassio de Campos

Interested?

Get in contact