Optimized realization of Bayesian networks in reduced normal form using latent variable model

Bayesian networks in their Factor Graph Reduced Normal Form are a powerful paradigm for implementing inference graphs. Unfortunately, the computational and memory costs of these networks may be considerable even for relatively small networks, and this is one of the main reasons why these structures have often been underused in practice. In this work, through a detailed algorithmic and structural analysis, various solutions for cost reduction are proposed. Moreover, an online version of the classic batch learning algorithm is also analysed, showing very similar results in an unsupervised context but with much better performance; which may be essential if multi-level structures are to be built. The solutions proposed, together with the possible online learning algorithm, are included in a C++ library that is quite efficient, especially if compared to the direct use of the well-known sum-product and Maximum Likelihood algorithms. The results obtained are discussed with particular reference to a Latent Variable Model structure.

Automated summary

Bayesian networks in their Factor Graph Reduced Normal Form can be powerful for implementing inference graphs, but the computational and memory costs may be high, leading to underuse in practice. This work presents various cost reduction solutions through algorithmic and structural analysis, and explores the performance of an online version of the classic batch learning algorithm.