Large Deviation Methods for Approximate Probabilistic Inference

01/30/2013
by   Michael Kearns, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/13/2013

Computing Upper and Lower Bounds on Likelihoods in Intractable Networks

We present deterministic techniques for computing upper and lower bounds...
research
03/20/2013

Search-based Methods to Bound Diagnostic Probabilities in Very Large Belief Nets

Since exact probabilistic inference is intractable in general for large ...
research
10/19/2012

Approximate Decomposition: A Method for Bounding and Estimating Probabilistic and Deterministic Queries

In this paper, we introduce a method for approximating the solution to i...
research
10/19/2012

Efficient Inference in Large Discrete Domains

In this paper we examine the problem of inference in Bayesian Networks w...
research
03/27/2013

Simulation Approaches to General Probabilistic Inference on Belief Networks

A number of algorithms have been developed to solve probabilistic infere...
research
03/13/2013

Towards Precision of Probabilistic Bounds Propagation

The DUCK-calculus presented here is a recent approach to cope with proba...
research
03/27/2013

A Randomized Approximation Algorithm of Logic Sampling

In recent years, researchers in decision analysis and artificial intelli...

Please sign up or login with your details

Forgot password? Click here to reset