Factored Particles for Scalable Monitoring

Abstract

Exact monitoring in dynamic Bayesian networks is intractable, so approximate algorithms are necessary. This paper presents a new family of approximate monitoring algorithms that combine the best qualities of the particle filtering and Boyen-Koller methods. Our algorithms maintain an approximate representation the belief state in the form of sets of factored particles, that correspond to samples of clusters of state variables. Empirical results show that our algorithms outperform both ordinary particle filtering and the Boyen-Koller algorithm on large systems.

Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002)

References in corpus (2)

• Tractable Inference for Complex Stochastic Processes
• The Factored Frontier Algorithm for Approximate Inference in DBNs

Cited by in corpus (5)

• Relational Dynamic Bayesian Networks
• Approximate Smoothing and Parameter Estimation in High-Dimensional State-Space Models
• Bagged filters for partially observed interacting systems
• Auxiliary Variables for Bayesian Inference in Multi-Class Queueing Networks
• Percolation Thresholds of Updated Posteriors for Tracking Causal Markov Processes in Complex Networks