Towards the full information chain theory: expected loss and information relevance

TL;DR

This paper develops a theoretical framework linking information accuracy and relevance, proposing an optimal question selection method to maximize problem-solving effectiveness by effectively utilizing available information sources.

Contribution

It introduces a novel framework connecting source accuracy to problem relevance and formulates an optimal information acquisition problem with a duality relationship.

Findings

Establishes a duality between pseudoenergy and loss quantities.

Proposes an optimal question selection strategy.

Provides a theoretical basis for maximizing information utility.

Abstract

When additional information sources are available, an important question for an agent solving a certain problem is how to optimally use the information the sources are capable of providing. A framework that relates information accuracy on the source side to information relevance on the problem side is proposed. An optimal information acquisition problem is formulated as that of question selection to maximize the loss reduction for the problem solved by the agent. A duality relationship between pseudoenergy (accuracy related) quantities on the source side and loss (relevance related) quantities on the problem side is observed.