Renormalization Group Flow as Optimal Transport

Abstract

We establish that Polchinski's equation for exact renormalization group flow is equivalent to the optimal transport gradient flow of a field-theoretic relative entropy. This provides a compelling information-theoretic formulation of the exact renormalization group, expressed in the language of optimal transport. A striking consequence is that a regularization of the relative entropy is in fact an RG monotone. We compute this monotone in several examples. Our results apply more broadly to other exact renormalization group flow equations, including widely used specializations of Wegner-Morris flow. Moreover, our optimal transport framework for RG allows us to reformulate RG flow as a variational problem. This enables new numerical techniques and establishes a systematic connection between neural network methods and RG flows of conventional field theories.

34+12 pages, 4 figures; v2: typos fixed, references and comments added; v3: more typos fixed, Appendix expanded

References in corpus (1)

• Manifestly Gauge Invariant QCD

Cited by in corpus (13)

• On the IR Divergences in de Sitter Space: loops, resummation and the semi-classical wavefunction
• Bayesian Renormalization
• Functional flows for complex effective actions
• Gravity from thermodynamics: optimal transport and negative effective dimensions
• Stochastic dynamics and the Polchinski equation: an introduction
• The Inverse of Exact Renormalization Group Flows as Statistical Inference
• Bayesian RG Flow in Neural Network Field Theories
• Functional renormalization group for signal detection and stochastic ergodicity breaking
• Wilsonian Renormalization of Neural Network Gaussian Processes
• NCoder -- A Quantum Field Theory approach to encoding data
• A Lindbladian for exact renormalization of density operators in QFT
• Monotonicity of RG flow in emergent dual holography of worldsheet nonlinear $\sigma$ model
• Journey from the Wilson exact RG towards the Wegner-Morris Fokker-Planck RG and the Carosso field-coarsening via Langevin stochastic processes