REVIEW 5 cited by
Renormalization Group Flow as Optimal Transport
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Renormalization Group Flow as Optimal Transport
read the original 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.
Forward citations
Cited by 5 Pith papers
-
Stochastic inflation from a non-equilibrium renormalization group
A generalized Fokker-Planck equation for stochastic inflation is derived from a Polchinski-type renormalization group flow on the density matrix, incorporating dissipative and diffusive corrections beyond the leading order.
-
Naturalness and Fisher Information
A fine-tuning measure is defined from the eigenvalues of a rescaled Fisher information matrix on parameter space, with a geometric interpretation as the pullback of the Euclidean metric from observable space.
-
Diffusion Models for Sampling Near Criticality in Lattice Field Theories
Fully convolutional diffusion models trained on small lattices transfer to unseen larger volumes for 2D/3D phi^4 sampling across phases, matching or beating same-size training on most observables.
-
Some universalities in the partition functions of low-dimensional gravity models
Conjectures universalities in partition functions across low-dimensional gravity models by examining similarities under parameter changes, wavefunction behaviors, entanglement, and wormhole connections.
-
Lecture Notes on Statistical Physics and Neural Networks
Lecture notes that treat statistical physics as probability theory and connect Ising models, spin glasses, and renormalization group ideas to Hopfield networks, restricted Boltzmann machines, and large language models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.