English
Related papers

Related papers: Bayesian RG Flow in Neural Network Field Theories

200 papers

Neural network field theory (NNFT) represents fields as neural networks and samples field configurations by drawing network parameters from a probability distribution. We identify a previously unexplored architectural freedom in NNFT,…

High Energy Physics - Theory · Physics 2026-05-01 Zhengkang Zhang

The gradient property of the renormalisation group (RG) is examined to four-loop order in scalar-fermion systems in $d=4$ and $d=4-\varepsilon$ dimensions. The crucial role played by the beta shift, which is a modification of the standard…

High Energy Physics - Theory · Physics 2025-11-05 William H. Pannell , William Patrick Ronayne , Andreas Stergiou

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

We introduce in this work the normalizing field flows (NFF) for learning random fields from scattered measurements. More precisely, we construct a bijective transformation (a normalizing flow characterizing by neural networks) between a…

Machine Learning · Computer Science 2022-05-11 Ling Guo , Hao Wu , Tao Zhou

Recurrent neural networks (RNNs) are widely used in computational neuroscience and machine learning applications. In an RNN, each neuron computes its output as a nonlinear function of its integrated input. While the importance of RNNs,…

Neurons and Cognition · Quantitative Biology 2012-07-10 Sebastian Bitzer , Stefan J. Kiebel

Binary Balanced Tree RvNNs (BBT-RvNNs) enforce sequence composition according to a preset balanced binary tree structure. Thus, their non-linear recursion depth is just $\log_2 n$ ($n$ being the sequence length). Such logarithmic scaling…

Machine Learning · Computer Science 2023-11-09 Jishnu Ray Chowdhury , Cornelia Caragea

General circulation models (GCMs) typically have a grid size of 25--200 km. Parametrizations are used to represent diabatic processes such as radiative transfer and cloud microphysics and account for sub-grid-scale motions and variability.…

Atmospheric and Oceanic Physics · Physics 2019-10-23 Noah D Brenowitz , Christopher S Bretherton

The random vector functional link (RVFL) network is a prominent classification model with strong generalization ability. However, RVFL treats all samples uniformly, ignoring whether they are pure or noisy, and its scalability is limited due…

Machine Learning · Computer Science 2024-09-26 M. Sajid , A. Quadir , M. Tanveer

We investigate the monotonicity of the renormalization group (RG) flow from the perspectives of nonequilibrium thermodynamics. Applying the Martin-Siggia-Rose formalism to the Wilsonian RG transformation, we incorporate the RG flow…

High Energy Physics - Theory · Physics 2023-12-29 Ki-Seok Kim , Shinsei Ryu

We explore the application of the nonperturbative functional renormalization group (NPFRG) within its most common approximation scheme based on truncations of the derivative expansion, to the $Z_2$-symmetric scalar $\varphi^4$ theory as the…

Statistical Mechanics · Physics 2026-03-24 Ivan Balog , Lucija Nora Farkaš , Maroje Marohnić , Gilles Tarjus

Coarse-graining is a molecular modeling technique in which an atomistic system is represented in a simplified fashion that retains the most significant system features that contribute to a target output, while removing the degrees of…

The application of Wilson's Numerical Renormalization Group (NRG) method to dissipative quantum impurity models, in particular the sub-ohmic spin-boson model, has led to conclusions regarding the quantum critical behavior which are in…

Statistical Mechanics · Physics 2012-03-16 Matthias Vojta

The present paper is the second of a series of publications that aim at investigating relevant directions to turn the nuclear energy density functional (EDF) method as an effective field theory (EFT). The EDF approach has known numerous…

Strongly Correlated Electrons · Physics 2024-03-07 Kilian Fraboulet , Jean-Paul Ebran

We study gauging operations (or group extensions) in (smeared) boundary conformal field theories (BCFTs) and bulk conformal field theories, and their applications to various phenomena in topologically ordered systems. We apply the resultant…

High Energy Physics - Theory · Physics 2025-08-22 Yoshiki Fukusumi

In this letter we study renormalization group (RG) flows between 2d conformal field theories enjoying extended higher-spin $\mathcal{W}$-symmetry. We propose a new class of RG flows between the diagonal minimal models of…

High Energy Physics - Theory · Physics 2026-01-27 Federico Ambrosino , Tomáš Procházka

Free-running Recurrent Neural Networks (RNNs), especially probabilistic models, generate an ongoing information flux that can be quantified with the mutual information $I\left[\vec{x}(t),\vec{x}(t\!+\!1)\right]$ between subsequent system…

Neurons and Cognition · Quantitative Biology 2023-10-18 Claus Metzner , Marius E. Yamakou , Dennis Voelkl , Achim Schilling , Patrick Krauss

Resting-state functional magnetic resonance imaging (rsfMRI) is a powerful tool for investigating the relationship between brain function and cognitive processes as it allows for the functional organization of the brain to be captured…

Machine Learning · Computer Science 2025-02-25 Bishal Thapaliya , Esra Akbas , Jiayu Chen , Raam Sapkota , Bhaskar Ray , Pranav Suresh , Vince Calhoun , Jingyu Liu

The conventional oblique parameters analyses of precision electroweak data can be consistently cast in the modern framework of the Standard Model effective field theory (SMEFT) when restrictions are imposed on the SMEFT parameter space so…

High Energy Physics - Phenomenology · Physics 2016-07-20 James D. Wells , Zhengkang Zhang

We study inflation as a "cosmic" renormalization-group flow. The flow, which encodes the dependence on the background metric, is described by a running coupling $\alpha $, which parametrizes the slow roll, a de Sitter free, analytic beta…

High Energy Physics - Theory · Physics 2021-11-02 Damiano Anselmi , Filippo Fruzza , Marco Piva

Convolutional neural nets (CNNs) have demonstrated remarkable performance in recent history. Such approaches tend to work in a unidirectional bottom-up feed-forward fashion. However, practical experience and biological evidence tells us…

Computer Vision and Pattern Recognition · Computer Science 2016-05-06 Peiyun Hu , Deva Ramanan