Geometric Analysis, PDEs & Mathematical Structures

There is a newer version of the record available.

Published December 30, 2025 | Version 1
Preprint Open

Information Geometry and the Variational Structure of Physical Dynamics: A Rigorous Foundation

Authors/Creators

  • 1. Independent

Description

We develop a mathematically rigorous variational principle on statistical manifolds equipped with the Fisher information metric. Starting from seven axioms characterizing
distinguishability between probability distributions, we prove that the Fisher metric is the unique (up to scaling) Riemannian structure satisfying these information-theoretic
requirements. We then demonstrate that geodesic motion on this manifold, subject to domain-specific constraint functionals, recovers the Euler-Lagrange equations of known dynamical systems across physics, evolutionary biology, and machine learning. Our main theoretical contributions include: (i) a complete proof of metric uniqueness via Chentsov’s theorem with minimal assumptions, (ii) rigorous derivations showing consistency with Hamiltonian mechanics, quantum unitary evolution, thermodynamic relaxation, replicator equations, and natural gradient descent, and (iii) novel predictions including quantum decoherence rate bounds and evolutionary speed limits. We emphasize that our framework provides a reformulation revealing structural unity, not a complete derivation of fundamental physical laws. All constraint functionals encoding domain-specific physics must be specified externally. Nevertheless, this geometric perspective yields new testable predictions and unifies previously disparate mathematical structures under a common information-theoretic foundation.

Files

Information Geometry and the Variational Structure of Physical Dynamics PDF 12.30.25 Publication.pdf

Files (1.2 MB)

Additional details

Related works

Is supplemented by
Dataset: 10.5281/zenodo.18102069 (DOI)

Software

Repository URL
https://doi.org/10.5281/zenodo.18102069
Programming language
Python
Development Status
Active

References

  • [1] Amari, S. I. (1985). Differential-Geometrical Methods in Statistics. Springer Lecture Notes in Statistics. [2] Amari, S. (1998). Natural gradient works efficiently in learning. Neural Computation, 10(2), 251-276. [3] Amari, S., & Nagaoka, H. (2000). Methods of Information Geometry. American Mathematical Society. [4] Arnold, V. I. (1989). Mathematical Methods of Classical Mechanics (2nd ed.). Springer. [5] Ashtekar, A., & Schilling, T. A. (1999). Geometrical formulation of quantum mechanics. In On Einstein's Path (pp. 23-65). Springer. [6] Ay, N., Jost, J., Lê, H. V., & Schwachhöfer, L. (2017). Information Geometry. Springer.[7] Braunstein, S. L., & Caves, C. M. (1994). Statistical distance and the geometry of quantum states. Physical Review Letters, 72(22), 3439-3443. [8] Campbell, L. L. (1986). An extended Čencov characterization of the information metric. Proceedings of the American Mathematical Society, 98(1), 135-141. [9] Catoni, O. (2007). PAC-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning. Institute of Mathematical Statistics. [10] Chentsov, N. N. (1982). Statistical Decision Rules and Optimal Inference. American Mathematical Society. [11] Cover, T. M., & Thomas, J. A. (2006). Elements of Information Theory (2nd ed.). Wiley. [12] Fisher, R. A. (1930). The Genetical Theory of Natural Selection. Oxford University Press. [13] Frank, S. A. (2009). Natural selection maximizes Fisher information. Journal of Evolutionary Biology, 22(2), 231-244. [14] Friston, K. (2010). The free-energy principle: a unified brain theory? Nature Reviews Neuroscience, 11(2), 127-138. [15] Gelfand, I. M., & Fomin, S. V. (2000). Calculus of Variations. Dover Publications. [16] Goldstein, H., Poole, C., & Safko, J. (2002). Classical Mechanics (3rd ed.). Addison- Wesley. [17] Harper, M. (2009). Information geometry and evolutionary game theory. arXiv preprint arXiv:0911.1383. [18] Helstrom, C. W. (1976). Quantum Detection and Estimation Theory. Academic Press. [19] Jarzynski, C. (1997). Nonequilibrium equality for free energy differences. Physical Review Letters, 78(14), 2690-2693. [20] Jaynes, E. T. (1957). Information theory and statistical mechanics. Physical Review, 106(4), 620-630. [21] Kawai, R., Parrondo, J. M., & Van den Broeck, C. (2007). Dissipation: The phase-space perspective. Physical Review Letters, 98(8), 080602. [22] Kibble, T. W. (1979). Geometrization of quantum mechanics. Communications in Mathematical Physics, 65(2), 189-201. [23] Lee, J. M. (2018). Introduction to Riemannian Manifolds (2nd ed.). Springer. [24] Lenski, R. E., Rose, M. R., Simpson, S. C., & Tadler, S. C. (1991). Long-term experimental evolution in Escherichia coli. I. Adaptation and divergence during 2,000 generations. The American Naturalist, 138(6), 1315-1341. [25] Marsden, J. E., & Ratiu, T. S. (1999). Introduction to Mechanics and Symmetry (2nd ed.). Springer. [26] Martens, J., & Grosse, R. (2015). Optimizing neural networks with Kronecker-factored approximate curvature. International Conference on Machine Learning, 2408-2417. [27] Martínez, I. A., Roldán, É., Dinis, L., Petrov, D., Parrondo, J. M., & Rica, R. A. (2016). Brownian Carnot engine. Nature Physics, 12(1), 67-70. [28] McAllester, D. A. (1999). PAC-Bayesian model averaging. In Proceedings of the Twelfth Annual Conference on Computational Learning Theory (pp. 164-170). [29] Petz, D. (1996). Monotone metrics on matrix spaces. Linear Algebra and its Applications, 244, 81-96. [30] Seifert, U. (2012). Stochastic thermodynamics, fluctuation theorems and molecular machines. Reports on Progress in Physics, 75(12), 126001. [31] Sorkin, R. D. (2003). Causal sets: Discrete gravity. In Lectures on Quantum Gravity (pp. 305-327). Springer. [32] Souriau, J. M. (1997). Structure of Dynamical Systems: A Symplectic View of Physics. Birkhäuser. [33] Wick, G. C. (1954). Properties of Bethe-Salpeter wave functions. Physical Review, 96(4), 1124-1134.