Quantifying the complexity of geodesic paths on curved statistical manifolds through information geometric entropies and Jacobi fields
From MaRDI portal
Publication:633725
DOI10.1016/J.PHYSD.2010.11.013zbMATH Open1217.37079arXiv1011.5555OpenAlexW2077048218MaRDI QIDQ633725FDOQ633725
Authors: Carlo Cafaro, Stefano Mancini 
Publication date: 29 March 2011
Published in: Physica D (Search for Journal in Brave)
Abstract: We characterize the complexity of geodesic paths on a curved statistical manifold M_{s} through the asymptotic computation of the information geometric complexity V_{M_{s}} and the Jacobi vector field intensity J_{M_{s}}. The manifold M_{s} is a 2l-dimensional Gaussian model reproduced by an appropriate embedding in a larger 4l-dimensional Gaussian manifold and endowed with a Fisher-Rao information metric g_{{mu}{
u}}({Theta}) with non-trivial off diagonal terms. These terms emerge due to the presence of a correlational structure (embedding constraints) among the statistical variables on the larger manifold and are characterized by macroscopic correlational coefficients r_{k}. First, we observe a power law decay of the information geometric complexity at a rate determined by the coefficients r_{k} and conclude that the non-trivial off diagonal terms lead to the emergence of an asymptotic information geometric compression of the explored macrostates {Theta} on M_{s}. Finally, we observe that the presence of such embedding constraints leads to an attenuation of the asymptotic exponential divergence of the Jacobi vector field intensity.
Full work available at URL: https://arxiv.org/abs/1011.5555
Recommendations
- Information geometric complexity of entropic motion on curved statistical manifolds under different metrizations of probability spaces
- Geometrodynamics of Information on Curved Statistical Manifolds and its Applications to Chaos
- Entropy and complexity of a path in sub-Riemannian geometry
- Softening the complexity of entropic motion on curved statistical manifolds
- A family of geometrical entropies for stochastic processes in path space
- Information geometry and asymptotic geodesics on the space of normal distributions
- Information-geometric indicators of chaos in Gaussian Models on statistical manifolds of negative Ricci Curvature
- Information geometric methods for complexity
- An estimate for the measure theoretic entropy of geodesic flows
- scientific article; zbMATH DE number 4048705
Strange attractors, chaotic dynamics of systems with hyperbolic behavior (37D45) Topological entropy (37B40) Dynamical systems in other branches of physics (quantum mechanics, general relativity, laser physics) (37N20)
Cites Work
- Stochastic complexity and modeling
- Title not available (Why is that?)
- CHARACTERISTIC LYAPUNOV EXPONENTS AND SMOOTH ERGODIC THEORY
- Title not available (Why is that?)
- On the relation between entropy and the average complexity of trajectories in dynamical systems
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Information-geometric indicators of chaos in Gaussian Models on statistical manifolds of negative Ricci Curvature
- Toward a quantitative theory of self-generated complexity
- Measures of statistical complexity: why?
- INFORMATION GEOMETRY, INFERENCE METHODS AND CHAOTIC ENERGY LEVELS STATISTICS
- Geometrodynamics of Information on Curved Statistical Manifolds and its Applications to Chaos
- Logical basis for information theory and probability theory
- Title not available (Why is that?)
- Jacobi fields on statistical manifolds of negative curvature
- Quantum computation as geometry
- The geometry of quantum computation
- What is complexity?
- Title not available (Why is that?)
- Complexities and their applications to characterization of chaos
- Title not available (Why is that?)
- Riemannian geometry of quantum computation
- The generalized Jacobi equation
- Uncertainty, predictability and decidability in chaotic dynamical systems
- On the complexity of statistical models admitting correlations
- Chaos and complexity of quantum motion
- How Many “Arrows of Time” Do We Really Need to Comprehend Statistical Laws?
Cited In (16)
- Local softening of information geometric indicators of chaos in statistical modeling in the presence of quantum-like considerations
- Application of the maximum relative entropy method to the physics of ferromagnetic materials
- On the complexity of statistical models admitting correlations
- An information geometric perspective on the complexity of macroscopic predictions arising from incomplete information
- Information geometric methods for complexity
- Information geometric complexity of a trivariate Gaussian statistical model
- Entropy and complexity of a path in sub-Riemannian geometry
- Information-geometric indicators of chaos in Gaussian Models on statistical manifolds of negative Ricci Curvature
- Notions of the ergodic hierarchy for curved statistical manifolds
- Information geometric complexity of entropic motion on curved statistical manifolds under different metrizations of probability spaces
- Theoretical investigations of an information geometric approach to complexity
- Hermite-Gaussian model for quantum states
- Softening the complexity of entropic motion on curved statistical manifolds
- Jacobi fields on statistical manifolds of negative curvature
- Learning on dynamic statistical manifolds
- Qubit geodesics on the Bloch sphere from optimal-speed Hamiltonian evolutions
This page was built for publication: Quantifying the complexity of geodesic paths on curved statistical manifolds through information geometric entropies and Jacobi fields
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q633725)
