Practical Aspects of Solving Hybrid Bayesian Networks Containing Deterministic Conditionals

Abstract

In this paper we discuss some practical issues that arise in solv- ing hybrid Bayesian networks that include deterministic conditionals for continuous variables. We show how exact inference can become intractable even for small networks, due to the di culty in handling deterministic conditionals (for continuous variables). We propose some strategies for carrying out the inference task using mixtures of polyno- mials and mixtures of truncated exponentials. Mixtures of polynomials can be de ned on hypercubes or hyper-rhombuses. We compare these two methods. A key strategy is to re-approximate large potentials with potentials consisting of fewer pieces and lower degrees/number of terms. We discuss several methods for re-approximating potentials. We illustrate our methods in a practical application consisting of solv- ing a stochastic PERT network.