Improving parameter learning of Bayesian nets from incomplete data

Details Improving parameter learning of Bayesian nets from incomplete data Improving parameter learning of Bayesian nets from incomplete data

2011-10-12

arxiv.org/abs/1110.3239v1

Computer Science

Learning

Scientific paper

This paper addresses the estimation of parameters of a Bayesian network from incomplete data. The task is usually tackled by running the Expectation-Maximization (EM) algorithm several times in order to obtain a high log-likelihood estimate. We argue that choosing the maximum log-likelihood estimate (as well as the maximum penalized log-likelihood and the maximum a posteriori estimate) has severe drawbacks, being affected both by overfitting and model uncertainty. Two ideas are discussed to overcome these issues: a maximum entropy approach and a Bayesian model averaging approach. Both ideas can be easily applied on top of EM, while the entropy idea can be also implemented in a more sophisticated way, through a dedicated non-linear solver. A vast set of experiments shows that these ideas produce significantly better estimates and inferences than the traditional and widely used maximum (penalized) log-likelihood and maximum a posteriori estimates. In particular, if EM is adopted as optimization engine, the model averaging approach is the best performing one; its performance is matched by the entropy approach when implemented using the non-linear solver. The results suggest that the applicability of these ideas is immediate (they are easy to implement and to integrate in currently available inference engines) and that they constitute a better way to learn Bayesian network parameters.

Affiliated with

Also associated with

No associations

Rating

Improving parameter learning of Bayesian nets from incomplete data does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Improving parameter learning of Bayesian nets from incomplete data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Improving parameter learning of Bayesian nets from incomplete data will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-634954