Abstraction in decision-makers with limited information processing capabilities

TL;DR

This paper explores how abstractions in decision-making arise from limited information processing capabilities, linking free-energy principles with rate-distortion theory to explain efficient information handling in humans, animals, and artificial systems.

Contribution

It establishes a theoretical connection between free-energy decision frameworks and rate-distortion theory, showing how abstractions naturally emerge from processing constraints.

Findings

Abstractions are induced by limits in information processing capacity.

Rate-distortion theory explains the emergence of abstractions in decision-making.

The framework unifies biological and artificial decision processes.

Abstract

A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise. From an information theoretic point of view abstractions are desirable because they allow for very efficient information processing. In artificial systems abstractions are often implemented through computationally costly formations of groups or clusters. In this work we establish the relation between the free-energy framework for decision making and rate-distortion theory and demonstrate how the application of rate-distortion for decision-making leads to the emergence of abstractions. We argue that abstractions are induced due to a limit in information processing capacity.