The Inverse of Exact Renormalization Group Flows as Statistical Inference

Abstract

We build on the view of the Exact Renormalization Group (ERG) as an instantiation of Optimal Transport described by a functional convection-diffusion equation. We provide a new information theoretic perspective for understanding the ERG through the intermediary of Bayesian Statistical Inference. This connection is facilitated by the Dynamical Bayesian Inference scheme, which encodes Bayesian inference in the form of a one parameter family of probability distributions solving an integro-differential equation derived from Bayes' law. In this note, we demonstrate how the Dynamical Bayesian Inference equation is, itself, equivalent to a diffusion equation which we dub Bayesian Diffusion. Identifying the features that define Bayesian Diffusion, and mapping them onto the features that define the ERG, we obtain a dictionary outlining how renormalization can be understood as the inverse of statistical inference.

52 pages, 3 tables. V2 Minor revisions, matches the published version of the text

References in corpus (26)

• The Large N Limit of Superconformal Field Theories and Supergravity
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• The Exact Renormalisation Group and Approximate Solutions
• Entanglement Renormalization and Holography
• Holographic quantum error-correcting codes: Toy models for the bulk/boundary correspondence
• Reconstruction of Bulk Operators within the Entanglement Wedge in Gauge-Gravity Duality
• Exact Renormalization Group Equations. An Introductory Review
• Seeing a c-theorem with holography
• Tensor Network Renormalization
• Derivative Expansion of the Exact Renormalization Group
• Fundamentals of the Exact Renormalization Group
• Elements of the Continuous Renormalization Group
• Holographic Geometry of Entanglement Renormalization in Quantum Field Theories
• Geometric Holography, the Renormalization Group and the c-Theorem
• Markov property of the CFT vacuum and the a-theorem
• A c-theorem for the entanglement entropy
• Universal recovery maps and approximate sufficiency of quantum relative entropy
• Canonical Energy is Quantum Fisher Information
• Exact Scheme Independence
• Non-commutative calculus, optimal transport and functional inequalities in dissipative quantum systems
• Holographic Geometry of cMERA for Quantum Quenches and Finite Temperature
• Information geometric approach to the renormalisation group
• The Holographic Geometry of the Renormalization Group and Higher Spin Symmetries
• The renormalisation group via statistical inference
• Renormalization Group Flow as Optimal Transport
• Bayesian Renormalization

Cited by in corpus (5)

• On learning higher-order cumulants in diffusion models
• Bayesian RG Flow in Neural Network Field Theories
• Quantum error correction realized by the renormalization group in scalar field theories
• Functional Renormalization for Signal Detection: Dimensional Analysis and Dimensional Phase Transition for Nearly Continuous Spectra Effective Field Theory
• Journey from the Wilson exact RG towards the Wegner-Morris Fokker-Planck RG and the Carosso field-coarsening via Langevin stochastic processes