Conserved active information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yanchen, Díaz-Pachón, Daniel Andrés
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908972547571712
author Chen, Yanchen
Díaz-Pachón, Daniel Andrés
author_facet Chen, Yanchen
Díaz-Pachón, Daniel Andrés
contents We introduce conserved active information $I^\oplus$, a symmetric extension of active information that quantifies net information gain/loss across the entire search space, respecting No-Free-Lunch conservation. Through Bernoulli and uniform-baseline examples, we show $I^\oplus$ reveals regimes hidden from KL divergence, such as when strong knowledge reduces global disorder. Such regimes are proven formally under uniform baseline, distinguishing disorder (increasing mild knowledge from order-imposing strong knowledge. We further illustrate these regimes with examples from Markov chains and cosmological fine-tuning. This resolves a longstanding critique of active information while enabling applications in search, optimization, and beyond.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21834
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conserved active information
Chen, Yanchen
Díaz-Pachón, Daniel Andrés
Neural and Evolutionary Computing
Computational Complexity
Human-Computer Interaction
Information Theory
94A15 (primary), 94A17 (primary), 60A05 (secondary), 62A01 (secondary), 68Q07 (secondary), 68Q15 (secondary)
F.1.3; F.2.3; H.1.1
We introduce conserved active information $I^\oplus$, a symmetric extension of active information that quantifies net information gain/loss across the entire search space, respecting No-Free-Lunch conservation. Through Bernoulli and uniform-baseline examples, we show $I^\oplus$ reveals regimes hidden from KL divergence, such as when strong knowledge reduces global disorder. Such regimes are proven formally under uniform baseline, distinguishing disorder (increasing mild knowledge from order-imposing strong knowledge. We further illustrate these regimes with examples from Markov chains and cosmological fine-tuning. This resolves a longstanding critique of active information while enabling applications in search, optimization, and beyond.
title Conserved active information
topic Neural and Evolutionary Computing
Computational Complexity
Human-Computer Interaction
Information Theory
94A15 (primary), 94A17 (primary), 60A05 (secondary), 62A01 (secondary), 68Q07 (secondary), 68Q15 (secondary)
F.1.3; F.2.3; H.1.1
url https://arxiv.org/abs/2512.21834