Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Kolpakov, Alexander
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.13543
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911215772499968
author Kolpakov, Alexander
author_facet Kolpakov, Alexander
contents We develop a framework for dualizing the Kolmogorov structure function $h_x(α)$, which then allows using computable complexity proxies. We establish a mathematical analogy between information-theoretic constructs and statistical mechanics, introducing a suitable partition function and free energy functional. We explicitly prove the Legendre-Fenchel duality between the structure function and free energy, showing detailed balance of the Metropolis kernel, and interpret acceptance probabilities as information-theoretic scattering amplitudes. A susceptibility-like variance of model complexity is shown to peak precisely at loss-complexity trade-offs interpreted as phase transitions. Practical experiments with linear and tree-based regression models verify these theoretical predictions, explicitly demonstrating the interplay between the model complexity, generalization, and overfitting threshold.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13543
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Loss-Complexity Landscape and Model Structure Functions
Kolpakov, Alexander
Information Theory
Artificial Intelligence
Machine Learning
Mathematical Physics
I.2.2; I.2.6
We develop a framework for dualizing the Kolmogorov structure function $h_x(α)$, which then allows using computable complexity proxies. We establish a mathematical analogy between information-theoretic constructs and statistical mechanics, introducing a suitable partition function and free energy functional. We explicitly prove the Legendre-Fenchel duality between the structure function and free energy, showing detailed balance of the Metropolis kernel, and interpret acceptance probabilities as information-theoretic scattering amplitudes. A susceptibility-like variance of model complexity is shown to peak precisely at loss-complexity trade-offs interpreted as phase transitions. Practical experiments with linear and tree-based regression models verify these theoretical predictions, explicitly demonstrating the interplay between the model complexity, generalization, and overfitting threshold.
title Loss-Complexity Landscape and Model Structure Functions
topic Information Theory
Artificial Intelligence
Machine Learning
Mathematical Physics
I.2.2; I.2.6
url https://arxiv.org/abs/2507.13543