Information Geometry and the Variational Structure of Physical Dynamics: A Rigorous Foundation
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 provevia Chentsov's theorem that the Fisher metric is the unique (up to a positive constant) Riemannian
structure satisfying these information-theoretic requirements. We then show that geodesic motion on this manifold, subject to domain-specific constraint functionals, recovers the equations of motion governing Hamiltonian mechanics, quantum unitary evolution, thermodynamic relaxation, evolutionary replicator dynamics,
and natural gradient descent. Our main contributions are: (i) a complete proof of metric uniqueness from physical axioms; (ii) rigorous consistency demonstrations with explicit error bounds; (iii) seven novel, falsifiable predictions - including quantum decoherence rate scaling with the quantum Fisher information, evolutionary speed limits, and neural network capacity scaling C ~ N0.6 three with preliminary numerical support; and (iv) explicit falsification criteria. We address anticipated criticisms, including the constraint problem, the signature problem, and questions of novelty beyond reformulation. We emphasize throughout that this framework is a reformulation revealing structural unity across disciplines, not a derivation of fundamental constants or a Theory of Everything. All constraint functionals encoding domain-specific physics must be specified externally. The mathematics is rigorous, the predictions are testable, and the question is well-posed. Now nature must answer.
Files
Information_Geometry final march.pdf
Files
(754.9 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:f6b182e60a7cf5f3e4f8b4665f1aea48
|
754.9 kB | Preview Download |
Additional details
Related works
- Is supplemented by
- Dataset: 10.5281/zenodo.19147422 (DOI)
Software
- Repository URL
- https://doi.org/10.5281/zenodo.18102069
- Programming language
- Python
- Development Status
- Active
References
- Abraham, R. and Marsden, J. E. (1978). Foundations of Mechanics, 2nd ed. Benjamin/ Cummings. Amari, S. I. (1985). Dierential-Geometrical Methods in Statistics. Springer. Amari, S. (1998). Natural gradient works eciently in learning. Neural Comput., 10(2):251276. Amari, S. and Nagaoka, H. (2000). Methods of Information Geometry. AMS/Oxford. Arnold, V. I. (1989). Mathematical Methods of Classical Mechanics, 2nd ed. Springer. Ashtekar, A. and Schilling, T. A. (1999). Geometrical formulation of quantum mechanics. In On Einstein's Path, pp. 2365. Springer. Ay, N., Jost, J., Lê, H. V., and Schwachhöfer, L. (2017). Information Geometry. Springer. Bengtsson, I. and ›yczkowski, K. (2006). Geometry of Quantum States. Cambridge University Press. Braunstein, S. L. and Caves, C. M. (1994). Statistical distance and the geometry of quantum states. Phys. Rev. Lett., 72(22):34393443. Brody, D. C. and Hughston, L.P. (2001). Geometric quantum mechanics. J. Geom. Phys., 38(1):1953. Campbell, L. L. (1986). An extended ƒencov characterization of the information metric. Proc. AMS, 98(1):135141. Chentsov, N. N. (1982). Statistical Decision Rules and Optimal Inference. AMS. Cover, T. M. and Thomas, J. A. (2006). Elements of Information Theory, 2nd ed. Wiley. Cramér, H. (1946). Mathematical Methods of Statistics. Princeton University Press. Crooks, G. E. (2007). Measuring thermodynamic length. Phys. Rev. Lett., 99:100602. do Carmo, M.P. (1992). Riemannian Geometry. Birkhäuser. Ewens, W. J. (2004). Mathematical Population Genetics, 2nd ed. Springer. Feynman, R.P. and Hibbs, A. R. (1965). Quantum Mechanics and Path Integrals. McGraw-Hill. Fisher, R. A. (1925). Theory of statistical estimation. Math. Proc. Cambridge Phil. Soc., 22(5):700725. Fisher, R. A. (1930). The Genetical Theory of Natural Selection. Oxford University Press. Frank, S. A. (2009). Natural selection maximizes Fisher information. J. Evol. Biol., 22(2):231244. Frank, S. A. (2012). Natural selection. V. How to read the fundamental equations. J. Evol. Biol., 25(12):23772396. Friston, K. (2010). The free-energy principle: a unied brain theory? Nature Rev. Neu- rosci., 11(2):127138. Gelfand, I. M. and Fomin, S. V. (2000). Calculus of Variations. Dover. Good, B. H., McDonald, M. J., Barrick, J. E., Lenski, R. E., and Desai, M. M. (2017). The dynamics of molecular evolution over 60,000 generations. Nature, 551:4550. Helstrom, C. W. (1976). Quantum Detection and Estimation Theory. Academic Press. Jaynes, E. T. (1957). Information theory and statistical mechanics. Phys. Rev., 106(4):620630. Kibble, T. W.B. (1979). Geometrization of quantum mechanics. Commun. Math. Phys., 65:189201. Lenski, R. E., Rose, M. R., Simpson, S. C., and Tadler, S. C. (1991). Long-term experimental evolution in Escherichia coli. I. Am. Nat., 138:13151341. Marsden, J. E. and Ratiu, T. S. (1999). Introduction to Mechanics and Symmetry, 2nd ed. Springer. McAllester, D. A. (1999). PAC-Bayesian model averaging. Proc. 12th COLT, pp. 164170. Morimoto, T. (1963). Markov processes and the H-theorem. J. Phys. Soc. Japan, 18(3):328331. Petz, D. (1996). Monotone metrics on matrix spaces. Linear Algebra Appl., 244:8196. Rao, C. R. (1945). Information and accuracy attainable in the estimation of statistical parameters. Bull. Calcutta Math. Soc., 37:8191. Ruppeiner, G. (1995). Riemannian geometry in thermodynamic uctuation theory. Rev. Mod. Phys., 67:605659. Seifert, U. (2012). Stochastic thermodynamics, uctuation theorems and molecular machines. Rep. Prog. Phys., 75:126001. Shahshahani, S. (1979). A new mathematical framework for the study of linkage and selection. Mem. AMS, 211. Sorkin, R.D. (2003). Causal sets: Discrete gravity. In Lectures on Quantum Gravity, pp. 305327. Springer. Weinhold, F. (1975). Metric geometry of equilibrium thermodynamics. J. Chem. Phys., 63:24792483.