On the Concentration of Expectation and Approximate Inference in Layered Networks

We present an analysis of concentration-of-expectation phenomena in layered Bayesian networks that use generalized linear models as the local conditional probabilities. This framework encompasses a wide variety of probability distributions, including both discrete and continuous random variables. We utilize ideas from large deviation analysis and the delta method to devise and evaluate a class of approximate inference algorithms for layered Bayesian networks that have superior asymptotic error bounds and very fast computation time.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: XuanLong Nguyen, Michael I. Jordan
• Keywords: Continuous Random Variables, Layered Bayesian Networks, Local Conditional Probabilities, NIPS 2003, NIPS 2007