Information-Geometric Grammar Principle: A Statistical-Geometric Framework for Adaptive Systems
- 1Instituto de Física La Plata (IFLP), Universidad Nacional de La Plata, La Plata 1900, Argentina
Abstract
We formulate an Information-Geometric Grammar Principle (IGGP) for adaptive systems in which grammatical admissibility, probabilistic realization, and statistical geometry are treated as distinct but connected levels of description. A grammar is represented by a state space together with a set of admissible productions and a probabilistic rule assigning weights to those productions. The resulting family of probability distributions defines a statistical manifold endowed with the Fisher information metric. We distinguish probabilistic adaptation, which changes probabilities while preserving the admissible grammar, from structural adaptation, which changes the set of admissible productions itself. For a fixed statistical manifold, an information-geometric action leads to geodesic equations and provides a coordinate-invariant criterion for locally economical statistical evolution. Interacting components generate a collective statistical manifold, where off-diagonal Fisher components quantify statistical coupling. We further identify the additional convexity and integrability conditions required for a Legendre representation and emphasize that a thermodynamic interpretation is conditional rather than automatic. The resulting framework provides a hierarchy from grammar to statistics, Fisher geometry, adaptive dynamics, collective organization, and, when additional conditions hold, information-geometric thermodynamics.
Related
- Information-Geometric Selection for Validation-Guided Ensembles of Extreme Learning Machines: The LEA-EELM Framework
- Walk/Zeta correspondence for quantum walks on path graphs: a pre-geometric structure implied by a generalized reflection principle
- A Geometric Derivation of the Einstein Equations from the Causal Action Principle
- A Geometric Principle for Path Selection in Directed Acyclic Graphs
- When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations
BibTeX
@article{plastino2026informationgeometric,
title = {{Information-Geometric Grammar Principle: A Statistical-Geometric Framework for Adaptive Systems}},
author = {Angelo Plastino},
journal = {Axioms},
year = {2026},
month = nov,
doi = {10.3390/axioms15110825},
url = {https://www.mdpi.com/2075-1680/15/11/825},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Information-Geometric Grammar Principle: A Statistical-Geometric Framework for Adaptive Systems
AU - Angelo Plastino
PY - 2026
DA - 2026/11/05
JO - Axioms
DO - 10.3390/axioms15110825
UR - https://www.mdpi.com/2075-1680/15/11/825
AB - We formulate an Information-Geometric Grammar Principle (IGGP) for adaptive systems in which grammatical admissibility, probabilistic realization, and statistical geometry are treated as distinct but connected levels of description. A grammar is represented by a state space together with a set of admissible productions and a probabilistic rule assigning weights to those productions. The resulting family of probability distributions defines a statistical manifold endowed with the Fisher information metric. We distinguish probabilistic adaptation, which changes probabilities while preserving the admissible grammar, from structural adaptation, which changes the set of admissible productions itself. For a fixed statistical manifold, an information-geometric action leads to geodesic equations and provides a coordinate-invariant criterion for locally economical statistical evolution. Interacting components generate a collective statistical manifold, where off-diagonal Fisher components quantify statistical coupling. We further identify the additional convexity and integrability conditions required for a Legendre representation and emphasize that a thermodynamic interpretation is conditional rather than automatic. The resulting framework provides a hierarchy from grammar to statistics, Fisher geometry, adaptive dynamics, collective organization, and, when additional conditions hold, information-geometric thermodynamics.
SN - 2075-1680
ER -