From influence diagrams to multi-operator cluster DAGs

TL;DR

This paper introduces the Multi-operator Cluster DAG architecture, a new method for influence diagrams that leverages their composite structure to achieve more efficient decompositions and potentially exponential computational gains.

Contribution

The paper presents a novel architecture that improves influence diagram solving by exploiting their composite nature for better problem decomposition.

Findings

Achieves improved constrained induced-width in influence diagram decompositions

Potentially exponential computational gains over existing architectures

Utilizes composite structure of influence diagrams for enhanced analysis

Abstract

There exist several architectures to solve influence diagrams using local computations, such as the Shenoy-Shafer, the HUGIN, or the Lazy Propagation architectures. They all extend usual variable elimination algorithms thanks to the use of so-called 'potentials'. In this paper, we introduce a new architecture, called the Multi-operator Cluster DAG architecture, which can produce decompositions with an improved constrained induced-width, and therefore induce potentially exponential gains. Its principle is to benefit from the composite nature of influence diagrams, instead of using uniform potentials, in order to better analyze the problem structure.