English
Related papers

Related papers: Nonperturbative renormalization for the neural net…

200 papers

The infinite disorder fixed point of the random transverse-field Ising model is expected to control the critical behavior of a large class of random quantum and stochastic systems having an order parameter with discrete symmetry. Here we…

Disordered Systems and Neural Networks · Physics 2015-05-19 Istvan A. Kovacs , Ferenc Igloi

This paper, in addition to our recent works, intends to explore the behavior of the Wetterich flow equations in the portion of the theory space spanned by non-branching melons constrained with Ward-identities. We focus on a rank-5…

High Energy Physics - Theory · Physics 2022-02-14 Vincent Lahoche , Dine Ousmane Samary

Unrenormalizable theories contain infinitely many free parameters. Considering these theories in terms of the Wilsonian renormalization group (RG), we suggest a method for removing this large ambiguity. Our basic assumption is the existence…

High Energy Physics - Theory · Physics 2014-11-18 Jisuke Kubo , Masanori Nunami

We propose a neural-network construction of Euclidean scalar quantum field theories from transformer attention heads, defining $n$-point correlators by averaging over random network parameters in the NN-QFT framework. For a single attention…

Machine Learning · Computer Science 2026-02-12 Dmitry S. Ageev , Yulia A. Ageeva

In this paper, we study three dimensional NL$\sigma$Ms within two kind of nonperturbative methods; WRG and large-N expansion. First, we investigate the renormalizability of some NL$\sigma$Ms using WRG equation. We find that some models have…

High Energy Physics - Theory · Physics 2007-05-23 Kiyoshi Higashijima , Etsuko Itou

We investigate the renormalization of ``nonlocal" interactions which arise as an infinite sum of higher derivative interactions in an effective field theory. Using dimensional regularization with minimal subtraction in a general scalar…

High Energy Physics - Phenomenology · Physics 2009-10-22 Vineer Bhansali

Large nonlinear recurrent neural networks with random couplings generate high-dimensional, potentially chaotic activity whose structure is of interest in neuroscience and other fields. A fundamental object encoding the collective structure…

Disordered Systems and Neural Networks · Physics 2026-05-06 David G. Clark

To gain a deeper understanding of the glassy phase in $p$-spin quantum models, this paper examines the dynamics of the $N$-vector $\bm{x} \in \mathbb{R}^N$ through the framework of renormalization group theory. First, we focus on…

Disordered Systems and Neural Networks · Physics 2025-09-24 Vincent Lahoche , Dine Ousmane Samary , Parham Radpay

Hamiltonian Renormalisation, as defined within this series of works, was derived from covariant Wilson renormalisation via Osterwalder-Schrader reconstruction. As such it directly applies to QFT with a true (physical) Hamiltonian bounded…

General Relativity and Quantum Cosmology · Physics 2022-07-19 T. Thiemann , E. -A. Zwicknagel

We present several approaches to renormalization in QFT: the multi-scale analysis in perturbative renormalization, the functional methods \`a la Wetterich equation, and the loop-vertex expansion in non-perturbative renormalization. While…

High Energy Physics - Theory · Physics 2014-01-31 Razvan Gurau , Vincent Rivasseau , Alessandro Sfondrini

We study pattern formation in class of a large-dimensional neural networks posed on random graphs and subject to spatio-temporal stochastic forcing. Under generic conditions on coupling and nodal dynamics, we prove that the network admits a…

Probability · Mathematics 2025-08-26 Daniele Avitabile , James MacLaurin

Random graphs offer a useful mathematical representation of a variety of real world complex networks. Exponential random graphs, for example, are particularly suited towards generating random graphs constrained to have specified statistical…

Statistical Mechanics · Physics 2026-02-09 Alessio Catanzaro , Diego Garlaschelli , Subodh P. Patil

We show that the holomorphic Wilsonian beta-function of a renormalizable asymptotically free supersymmetric gauge theory with an arbitrary semi-simple gauge group, matter content, and renormalizable superpotential is exhausted at 1-loop…

High Energy Physics - Theory · Physics 2014-11-18 Michael Graesser , Bogdan Morariu

The renormalization group (RG) is an essential technique in statistical physics and quantum field theory, which considers scale-invariant properties of physical theories and how these theories' parameters change with scaling. Deep learning…

Statistical Mechanics · Physics 2023-08-23 Kelsie Taylor

We propose a renormalization scheme for non-local Quantum Field Theories (QFTs) with infinite derivatives inspired by string theory. Our Non-locality Renormalization Scheme (NRS) is inspired by Dimensional Regularization (DR) in local QFTs…

High Energy Physics - Theory · Physics 2023-04-18 Fayez Abu-Ajamieh , Sudhir K. Vempati

The general prescription for constructing the continuum limit of a field theory is explained using Wilson's renormalization group. We then formulate the renormalization group in perturbation theory and apply it to the four dimensional phi4…

High Energy Physics - Theory · Physics 2007-05-23 Hidenori Sonoda

We show that artificial neural networks (ANNs) can, to high accuracy, determine the topological invariant of a disordered system given its two-dimensional real-space Hamiltonian. Furthermore, we describe a "renormalization-group" (RG)…

Disordered Systems and Neural Networks · Physics 2022-06-22 Gilad Margalit , Omri Lesser , T. Pereg-Barnea , Yuval Oreg

An exact renormalization group for theories of a scalar chiral superfield is formulated, directly in four dimensional Euclidean space. By constructing a projector which isolates the superpotential from the full Wilsonian effective action,…

High Energy Physics - Theory · Physics 2015-03-13 Oliver J. Rosten

In holographic duality, dynamics along the emergent extra-dimensional space describes a renormalization group (RG) flow of the corresponding quantum field theory (QFT). Following this idea, we develop an emergent holographic description of…

High Energy Physics - Theory · Physics 2022-04-27 Ki-Seok Kim , Shinsei Ryu , Kanghoon Lee

Neural network field theory (NN-FT) formulates field theory in terms of a network architecture and a density on its parameters. We derive Schwinger--Dyson equations and Ward identities in NN-FT and utilize them to study anomalies. The…

High Energy Physics - Theory · Physics 2026-05-13 Christian Ferko , Samuel Frank , James Halverson , Vishnu Jejjala