The Information-Theoretic Imperative: Compression and the Epistemic Foundations of Intelligence

TL;DR

This work proposes the Information-Theoretic Imperative (ITI) and the Compression Efficiency Principle (CEP) as a universal, mechanism-level theory linking persistence under uncertainty to the emergence of reality-aligned intelligence. ITI states that systems must minimize epistemic entropy through predictive compression, while CEP explains why efficient compression mechanically favors generative, causal models over superficial patterns, via exception-accumulation dynamics and hierarchical amplification. Together they form a causal chain—from survival pressure to prediction, compression, generative-structure discovery, and reality alignment—applicable to biological, artificial, and multi-scale systems. The framework yields testable predictions: compression efficiency predicts out-of-distribution generalization, exception accumulation signals causal versus correlational structure, hierarchical systems show increasing efficiency across abstraction layers, and metabolic costs track representational complexity. The theory offers a unifying lens for understanding intelligence across domains, while remaining falsifiable through controlled empirical investigations of efficiency metrics, hierarchical depth, and thermodynamic coupling to information processing.

Abstract

Existing frameworks converge on the centrality of compression to intelligence but leave underspecified why this process enforces the discovery of causal structure rather than superficial statistical patterns. We introduce a two-level framework to address this gap. The Information-Theoretic Imperative (ITI) establishes that any system persisting in uncertain environments must minimize epistemic entropy through predictive compression: this is the evolutionary "why" linking survival pressure to information-processing demands. The Compression Efficiency Principle (CEP) specifies how efficient compression mechanically selects for generative, causal models through exception-accumulation dynamics, making reality alignment a consequence rather than a contingent achievement. Together, ITI and CEP define a causal chain: from survival pressure to prediction necessity, compression requirement, efficiency optimization, generative structure discovery, and ultimately reality alignment. Each link follows from physical, information-theoretic, or evolutionary constraints, implying that intelligence is the mechanically necessary outcome of persistence in structured environments. This framework yields empirically testable predictions: compression efficiency, measured as approach to the rate-distortion frontier, correlates with out-of-distribution generalization; exception-accumulation rates differentiate causal from correlational models; hierarchical systems exhibit increasing efficiency across abstraction layers; and biological systems demonstrate metabolic costs that track representational complexity. ITI and CEP thereby provide a unified account of convergence across biological, artificial, and multi-scale systems, addressing the epistemic and functional dimensions of intelligence without invoking assumptions about consciousness or subjective experience.