Algorithmic Free Energy Minimization: A New Foundation for Parsimonious Artificial Intelligence

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autore principale: Fathi, Kevin
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901678578466816
author Fathi, Kevin
author_facet Fathi, Kevin
contents <p>The dominant paradigm in modern Artificial Intelligence relies on maximizing performance metrics using massively overparameterized models trained via brute-force computation. This approach suffers from fundamental limitations in generalization, efficiency, and interpretability. We propose a new foundation based on the minimization of Algorithmic Free Energy (AFE). Derived from Algorithmic Information Theory, AFE provides a rigorous formalization of Occam's razor by unifying model complexity (Kolmogorov complexity) and data fit within a single objective: the expected total description length. We derive novel generalization bounds using the PAC-Bayesian framework under the normalized universal prior. We rigorously define this prior and the corresponding likelihood via STOP-symbol completion, ensuring uniform $O(1)$ constants. We prove two key results: (1) for bounded losses, the generalization gap is rigorously controlled by the expected algorithmic complexity of the hypotheses; (2) for the KL risk (log loss), the expected generalization error is tightly bounded by the normalized AFE (minus posterior entropy). These results demonstrate that minimizing AFE directly tightens provable upper bounds on generalization error. Although AFE is uncomputable, we prove that computable surrogates (Computable Free Energy, CFE) provide practical objectives that yield valid (possibly looser) generalization bounds. AFE minimization provides a principled path toward AI that is inherently parsimonious, efficient, and robust.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17560581
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Algorithmic Free Energy Minimization: A New Foundation for Parsimonious Artificial Intelligence
Fathi, Kevin
Algorithmic free energy
Kolmogorov complexity
Algorithmic information theory
Minimum description length
PAC-Bayesian bounds
Generalization error
Universal prior
STOP completion
Variational free energy
Occam's razor
Parsimonious artificial intelligence
Model complexity
Description length
Sample complexity
Computable free energy
Compression-based learning
Bayesian inference
Deep learning theory
<p>The dominant paradigm in modern Artificial Intelligence relies on maximizing performance metrics using massively overparameterized models trained via brute-force computation. This approach suffers from fundamental limitations in generalization, efficiency, and interpretability. We propose a new foundation based on the minimization of Algorithmic Free Energy (AFE). Derived from Algorithmic Information Theory, AFE provides a rigorous formalization of Occam's razor by unifying model complexity (Kolmogorov complexity) and data fit within a single objective: the expected total description length. We derive novel generalization bounds using the PAC-Bayesian framework under the normalized universal prior. We rigorously define this prior and the corresponding likelihood via STOP-symbol completion, ensuring uniform $O(1)$ constants. We prove two key results: (1) for bounded losses, the generalization gap is rigorously controlled by the expected algorithmic complexity of the hypotheses; (2) for the KL risk (log loss), the expected generalization error is tightly bounded by the normalized AFE (minus posterior entropy). These results demonstrate that minimizing AFE directly tightens provable upper bounds on generalization error. Although AFE is uncomputable, we prove that computable surrogates (Computable Free Energy, CFE) provide practical objectives that yield valid (possibly looser) generalization bounds. AFE minimization provides a principled path toward AI that is inherently parsimonious, efficient, and robust.</p>
title Algorithmic Free Energy Minimization: A New Foundation for Parsimonious Artificial Intelligence
topic Algorithmic free energy
Kolmogorov complexity
Algorithmic information theory
Minimum description length
PAC-Bayesian bounds
Generalization error
Universal prior
STOP completion
Variational free energy
Occam's razor
Parsimonious artificial intelligence
Model complexity
Description length
Sample complexity
Computable free energy
Compression-based learning
Bayesian inference
Deep learning theory
url https://doi.org/10.5281/zenodo.17560581