Watts-per-Intelligence Part II: Algorithmic Catalysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Perrier, Elija
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917430285041664
author Perrier, Elija
author_facet Perrier, Elija
contents We develop a thermodynamic theory of algorithmic catalysis within the watts-per-intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class-specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that installing this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for a catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within a unified information-thermodynamic constraint on intelligent computation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20897
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Watts-per-Intelligence Part II: Algorithmic Catalysis
Perrier, Elija
Information Theory
Artificial Intelligence
Computational Physics
We develop a thermodynamic theory of algorithmic catalysis within the watts-per-intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class-specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that installing this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for a catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within a unified information-thermodynamic constraint on intelligent computation.
title Watts-per-Intelligence Part II: Algorithmic Catalysis
topic Information Theory
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2604.20897