A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)

TL;DR

This paper proposes a model-free, information-theoretic framework for machine learning that directly analyzes raw data using surprisal, enhancing interpretability, flexibility, and efficiency across diverse tasks without relying on explicit models.

Contribution

It introduces a novel, unified approach based on uncertainty measurement that eliminates the need for distribution modeling and improves interpretability and adaptability in machine learning.

Findings

Achieves near state-of-the-art performance on common tasks

Enables direct data edits and deletions for model updates

Provides a unified, interpretable framework applicable to complex data types

Abstract

Traditional machine learning relies on explicit models and domain assumptions, limiting flexibility and interpretability. We introduce a model-free framework using surprisal (information theoretic uncertainty) to directly analyze and perform inferences from raw data, eliminating distribution modeling, reducing bias, and enabling efficient updates including direct edits and deletion of training data. By quantifying relevance through uncertainty, the approach enables generalizable inference across tasks including generative inference, causal discovery, anomaly detection, and time series forecasting. It emphasizes traceability, interpretability, and data-driven decision making, offering a unified, human-understandable framework for machine learning, and achieves at or near state-of-the-art performance across most common machine learning tasks. The mathematical foundations create a ``physics'' of information, which enable these techniques to apply effectively to a wide variety of complex data types, including missing data. Empirical results indicate that this may be a viable alternative path to neural networks with regard to scalable machine learning and artificial intelligence that can maintain human understandability of the underlying mechanics.