English
Related papers

Related papers: Gauge-covariant stochastic neural fields: Stabilit…

200 papers

Two algorithms are proposed to simulate space-time Gaussian random fields with a covariance function belonging to an extended Gneiting class, the definition of which depends on a completely monotone function associated with the spatial…

Computation · Statistics 2019-12-05 Denis Allard , Xavier Emery , Céline Lacaux , Christian Lantuéjoul

Gauge invariance is essential for making physically meaningful predictions. In superconductors, mean-field Hamiltonians that explicitly break $U(1)$ symmetry often yield gauge-dependent results. While this issue has been resolved for linear…

Superconductivity · Physics 2025-05-19 Sena Watanabe , Haruki Watanabe

We describe the fully gauge invariant cosmological perturbation equations in teleparallel gravity by using the gauge covariant version of the Stewart lemma for obtaining the variations in tetrad perturbations. In teleparallel theory,…

General Relativity and Quantum Cosmology · Physics 2016-05-31 A. Behboodi , S. Akhshabi , K. Nozari

Spatial Gaussian process regression models typically contain finite dimensional covariance parameters that need to be estimated from the data. We study the Bayesian estimation of covariance parameters including the nugget parameter in a…

Statistics Theory · Mathematics 2023-02-22 Cheng Li , Saifei Sun , Yichen Zhu

Linear cosmological perturbation theory is pivotal to a theoretical understanding of current cosmological experimental data provided e.g. by cosmic microwave anisotropy probes. A key issue in that theory is to extract the gauge invariant…

General Relativity and Quantum Cosmology · Physics 2010-02-17 K. Giesel , S. Hofmann , T. Thiemann , O. Winkler

In this paper we present a general framework in which one can rigorously study the effect of spatio-temporal noise on traveling waves, stationary patterns and oscillations that are invariant under the action of a finite-dimensional set of…

Dynamical Systems · Mathematics 2020-06-24 James MacLaurin

The main results are: 1. A manifestly covariant technique for the calculation of De Witt coefficients is elaborated; 2. The coefficients $a_3$ and $a_4$ are calculated; 3. Covariant methods for the study of the nonlocal structure of the…

High Energy Physics - Theory · Physics 2008-02-03 Ivan G. Avramidi

We introduce a functional covariant differential as a tool for studying field space geometry in a manifestly covariant way. We then touch upon its role in gauge theories and general relativity over bounded regions, and in BRST symmetry. Due…

Mathematical Physics · Physics 2017-06-26 Henrique Gomes , Aldo Riello

Stochastic neurons and hard non-linearities can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such…

Machine Learning · Computer Science 2013-08-16 Yoshua Bengio , Nicholas Léonard , Aaron Courville

This work theoretically studies stochastic neural networks, a main type of neural network in use. We prove that as the width of an optimized stochastic neural network tends to infinity, its predictive variance on the training set decreases…

Machine Learning · Computer Science 2022-05-25 Liu Ziyin , Hanlin Zhang , Xiangming Meng , Yuting Lu , Eric Xing , Masahito Ueda

We make a perturbative analysis of the number of degrees of freedom in a large class of metric theories respecting spatial symmetries, of which the Lagrangian includes kinetic terms of both the spatial metric and the lapse function. We show…

General Relativity and Quantum Cosmology · Physics 2019-05-13 Xian Gao , Chao Kang , Zhi-Bang Yao

This paper concerns the homogenization of Schrodinger equations for non-crystalline matter, that is to say the coefficients are given by the composition of stationary functions with stochastic deformations. Two rigorous results of so-called…

Analysis of PDEs · Mathematics 2022-06-03 Vernny Ccajma , Wladimir Neves , Jean Silva

We look into the fluctuations caused by disturbances in power systems. In the linearized system of the power systems, the disturbance is modeled by a Brownian motion process, and the fluctuations are described by the covariance matrix of…

Systems and Control · Electrical Eng. & Systems 2023-03-20 Xian Wu , Kaihua Xi , Aijie Cheng , Hai Xiang Lin , Jan H van Schuppen , Chenghui Zhang

This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coordinate rigidity and fitted effective-rank windows, we study how dominant singular…

Machine Learning · Computer Science 2026-05-05 Ziran Liu , Wei Wang , Jinhao Wang , Pengcheng Wang , Xinyi Sui , Cihan Ruan , Nam Ling , Wei Jiang

We construct the covariant effective field theory of gravity as an expansion in inverse powers of the Planck mass, identifying the leading and next-to-leading quantum corrections. We determine the form of the effective action for the cases…

General Relativity and Quantum Cosmology · Physics 2016-11-08 Alessandro Codello , Rajeev Kumar Jain

In the present paper the gauge-invariant formalism is developed for perturbations of the brane-world model in which our universe is realized as a boundary of a higher-dimensional spacetime. For the background model in which the bulk…

High Energy Physics - Theory · Physics 2009-10-31 Hideo Kodama , Akihiro Ishibashi , Osamu Seto

In this paper we study the dynamics of a statistical ensemble of strings, building on a recently proposed gauge theory of the string geodesic field. We show that this stochastic approach is equivalent to the Carath\'eodory formulation of…

High Energy Physics - Theory · Physics 2019-08-17 A. Aurilia , E. Spallucci , I. Vanzetta

Gravitational perturbations of anti-deSitter spacetime play important roles in AdS/CFT correspondence and the brane world scenario. In this paper, we develop a gauge-invariant formalism of gravitational perturbations of maximally symmetric…

High Energy Physics - Theory · Physics 2009-10-31 Shinji Mukohyama

Consistent interactions that can be added to a free, Abelian gauge theory comprising a BF model and a finite set of massless real scalar fields are constructed from the deformation of the solution to the master equation based on specific…

High Energy Physics - Theory · Physics 2016-07-06 Constantin Bizdadea , Solange-Odile Saliu

We analyze feature learning in infinite-width neural networks trained with gradient flow through a self-consistent dynamical field theory. We construct a collection of deterministic dynamical order parameters which are inner-product kernels…

Machine Learning · Statistics 2022-10-05 Blake Bordelon , Cengiz Pehlevan