Exploiting Evidence in Probabilistic Inference
This work addresses efficiency in probabilistic inference for domains like genetic linkage analysis, but it appears incremental as it builds on existing compilation methods.
The paper tackles the problem of compiling Bayesian networks with evidence using logical processing, achieving practical advantages in applications like maximum likelihood estimation and MAP computations, and empirically outperforms the quickscore algorithm in noisy-or networks.
We define the notion of compiling a Bayesian network with evidence and provide a specific approach for evidence-based compilation, which makes use of logical processing. The approach is practical and advantageous in a number of application areas-including maximum likelihood estimation, sensitivity analysis, and MAP computations-and we provide specific empirical results in the domain of genetic linkage analysis. We also show that the approach is applicable for networks that do not contain determinism, and show that it empirically subsumes the performance of the quickscore algorithm when applied to noisy-or networks.