Update Rules for Parameter Estimation in Bayesian Networks

This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [12]. We provide a unified framework for parameter estimation that encompasses both on-line learning, where the model is continuouslyadapted to new data cases as they arrive, and the more traditional batch learning, where a pre-accumulated set of samples is used in a one-time model selection process. In the batch case, our framework encompassesboth the gradient projection algorithm [2, 3] and the EM algorithm [14] for Bayesian networks. The framework also leads to new on-line and batch parameter update schemes, including a parameterized version of EM. We provide both empirical and theoretical results indicating that parameterized EM allows faster convergence to the maximum likelihood parameters than does standard EM.

• Type: Conference
• Year: 1997
• Where: UAI
• Authors: Eric Bauer, Daphne Koller, Yoram Singer
• Keywords: Bayesian Networks, On-line Learning, Parameter Estimation, UAI 1997, UAI 2008