Information Length Analysis of Linear Autonomous Stochastic Processes

When studying the behaviour of complex dynamical systems, a statistical formulation can provide useful insights. In particular, information geometry is a promising tool for this purpose. In this paper, we investigate the information length for n-dimensional linear autonomous stochastic processes, providing a basic theoretical framework that can be applied to a large set of problems in engineering and physics. A specific application is made to a harmonically bound particle system with the natural oscillation frequency ω, subject to a damping γ and a Gaussian white-noise. We explore how the information length depends on ω and γ, elucidating the role of critical damping γ=2ω in information geometry. Furthermore, in the long time limit, we show that the information length reflects the linear geometry associated with the Gaussian statistics in a linear stochastic process.

[1]  S. Nicholson,et al.  Geometric method for forming periodic orbits in the Lorenz system , 2016 .

[2]  C. Villani,et al.  Generalization of an Inequality by Talagrand and Links with the Logarithmic Sobolev Inequality , 2000 .

[3]  Carlos Gershenson,et al.  Guiding the Self-Organization of Cyber-Physical Systems , 2019, Frontiers in Robotics and AI.

[4]  S. Nicholson,et al.  Investigation of the statistical distance to reach stationary distributions , 2015 .

[5]  Angelo Plastino,et al.  Distances in Probability Space and the Statistical Complexity Setup , 2011, Entropy.

[6]  Eun-Jin Kim,et al.  Investigating Information Geometry in Classical and Quantum Systems through Information Length , 2018, Entropy.

[7]  Juan C. Correa,et al.  Metrics of Emergence, Self-Organization, and Complexity for EWOM Research , 2020, Frontiers in Physics.

[9]  James Heseltine,et al.  Novel mapping in non-equilibrium stochastic processes , 2016 .

[10]  Todd D. Murphey,et al.  Trajectory Synthesis for Fisher Information Maximization , 2014, IEEE Transactions on Robotics.

[11]  Rainer Hollerbach,et al.  Signature of nonlinear damping in geometric structure of a nonequilibrium process. , 2017, Physical review. E.

[12]  A. Dechant,et al.  Stochastic Time Evolution, Information Geometry, and the Cramér-Rao Bound , 2018, Physical Review X.

[13]  Jorge Cadima,et al.  Principal component analysis: a review and recent developments , 2016, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[14]  S. Velasco.  On the Brownian motion of a harmonically bound particle and the theory of a Wiener process , 1985 .

[15]  James Heseltine,et al.  Comparing Information Metrics for a Coupled Ornstein–Uhlenbeck Process , 2019, Entropy.

[16]  Ram Zamir,et al.  A Proof of the Fisher Information Inequality via a Data Processing Argument , 1998, IEEE Trans. Inf. Theory.

[17]  Karl J. Friston,et al.  Is the Free-Energy Principle a Formal Theory of Semantics? From Variational Density Dynamics to Neural and Phenotypic Representations , 2020, Entropy.

[18]  Karl J. Friston,et al.  Markov blankets, information geometry and stochastic thermodynamics , 2019, Philosophical Transactions of the Royal Society A.

[19]  W. Gangbo,et al.  The geometry of optimal transportation , 1996 .

[20]  Peter Harremoës,et al.  Rényi Divergence and Kullback-Leibler Divergence , 2012, IEEE Transactions on Information Theory.

[21]  Asuka Takatsu.  Wasserstein geometry of Gaussian measures , 2011 .

[22]  J. Lott.  Some Geometric Calculations on Wasserstein Space , 2006, math/0612562.

[23]  Eun Jin Kim,et al.  Information length in quantum systems , 2018 .

[24]  Eun-Jin Kim,et al.  Information Geometry of Nonlinear Stochastic Systems , 2018, Entropy.

[25]  James Heseltine,et al.  Geometric structure and geodesic in a solvable model of nonequilibrium process. , 2016, Physical review. E.

[26]  Mikhail Prokopenko,et al.  Entropy Methods in Guided Self-Organisation , 2014, Entropy.

[27]  Sueli I. Rodrigues Costa,et al.  Fisher information distance: a geometrical reading? , 2012, Discret. Appl. Math..

[28]  Expectations of products of random quadratic forms , 1986 .

[29]  Osvaldo A. Rosso,et al.  Statistical complexity and disequilibrium , 2003 .