Towards Practical Bayesian Parameter and State Estimation

TL;DR

This paper introduces a hybrid blackbox algorithm combining particle filtering and assumed density filtering for efficient online joint state and parameter estimation in dynamic Bayesian networks, applicable to discrete and continuous spaces.

Contribution

It presents a novel, efficient, and general online inference algorithm that handles both discrete and continuous parameters without problem-specific modifications.

Findings

More accurate results within fixed computation budgets

Applicable to both discrete and continuous parameter spaces

Demonstrated on toy and real models

Abstract

Joint state and parameter estimation is a core problem for dynamic Bayesian networks. Although modern probabilistic inference toolkits make it relatively easy to specify large and practically relevant probabilistic models, the silver bullet---an efficient and general online inference algorithm for such problems---remains elusive, forcing users to write special-purpose code for each application. We propose a novel blackbox algorithm -- a hybrid of particle filtering for state variables and assumed density filtering for parameter variables. It has following advantages: (a) it is efficient due to its online nature, and (b) it is applicable to both discrete and continuous parameter spaces . On a variety of toy and real models, our system is able to generate more accurate results within a fixed computation budget. This preliminary evidence indicates that the proposed approach is likely to be of practical use.