Information loss under coarse-graining: a geometric approach
arXiv:1710.05787 · doi:10.1103/PhysRevE.98.052112
Abstract
We use information geometry, in which the local distance between models measures their distinguishability from data, to quantify the flow of information under the renormalization group. We show that information about relevant parameters is preserved, with distances along relevant directions maintained under flow. By contrast, irrelevant parameters become less distinguishable under the flow, with distances along irrelevant directions contracting according to renormalization group exponents. We develop a covariant formalism to understand the contraction of the model manifold. We then apply our tools to understand the emergence of the diffusion equation and more general statistical systems described by a free energy. Our results give an information-theoretic justification of universality in terms of the flow of the model manifold under coarse-graining.
arXiv commentNew title, fixed typos
References in corpus (8)
- Geometrothermodynamics
- Parameter Space Compression Underlies Emergent Theories and Predictive Models
- Hysteresis, Avalanches, and Disorder Induced Critical Scaling: A Renormalization Group Approach
- Renormalization Group Theory for Global Asymptotic Analysis
- The geometry of nonlinear least squares with applications to sloppy models and optimization
- Renormalization Group and Probability Theory
- Fully developed isotropic turbulence: nonperturbative renormalization group formalism and fixed point solution
- Information geometric approach to the renormalisation group