Large Deviation Methods for Approximate Probabilistic Inference

Abstract

We study two-layer belief networks of binary random variables in which the conditional probabilities Pr[childlparents] depend monotonically on weighted sums of the parents. In large networks where exact probabilistic inference is intractable, we show how to compute upper and lower bounds on many probabilities of interest. In particular, using methods from large deviation theory, we derive rigorous bounds on marginal probabilities such as Pr[children] and prove rates of convergence for the accuracy of our bounds as a function of network size. Our results apply to networks with generic transfer function parameterizations of the conditional probability tables, such as sigmoid and noisy-OR. They also explicitly illustrate the types of averaging behavior that can simplify the problem of inference in large networks.

Appears in Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998)

Cited by in corpus (5)

• Exact value for subgaussian norm of centered indicator random variable
• The Kearns--Saul inequality for Bernoulli and Poisson-binomial distributions
• Subgaussian and strictly subgaussian random variable
• Novel Bernstein-like Concentration Inequalities for the Missing Mass
• On the Concentration of the Missing Mass