Variational Probabilistic Inference and the QMR-DT Network

TL;DR

This paper introduces a variational approximation method for efficient probabilistic inference in large-scale models like the QMR network, offering a deterministic alternative to stochastic sampling with promising results.

Contribution

It presents a novel variational inference approach tailored for large probabilistic models such as the QMR network, improving efficiency over existing stochastic methods.

Findings

The variational method provides accurate approximations in large-scale diagnostic models.

It outperforms stochastic sampling in computational efficiency.

The approach is feasible for real-world medical diagnosis applications.

Abstract

We describe a variational approximation method for efficient inference in large-scale probabilistic models. Variational methods are deterministic procedures that provide approximations to marginal and conditional probabilities of interest. They provide alternatives to approximate inference methods based on stochastic sampling or search. We describe a variational approach to the problem of diagnostic inference in the `Quick Medical Reference' (QMR) network. The QMR network is a large-scale probabilistic graphical model built on statistical and expert knowledge. Exact probabilistic inference is infeasible in this model for all but a small set of cases. We evaluate our variational inference algorithm on a large set of diagnostic test cases, comparing the algorithm to a state-of-the-art stochastic sampling method.