English
Related papers

Related papers: Higher order extensions of the Gaussian effective …

200 papers

We evaluate the thermal corrections to the generalized Gaussian effective potential. We carry out the calculations of the lowest order corrections in the case of self-interacting scalar fields in one and two spatial dimensions, and study…

High Energy Physics - Phenomenology · Physics 2008-02-03 Paolo Cea , Luigi Tedesco

Gaussian process classification is a popular method with a number of appealing properties. We show how to scale the model within a variational inducing point framework, outperforming the state of the art on benchmark datasets. Importantly,…

Machine Learning · Statistics 2014-11-10 James Hensman , Alex Matthews , Zoubin Ghahramani

The Poisson model is frequently employed to describe count data, but in a Bayesian context it leads to an analytically intractable posterior probability distribution. In this work, we analyze a variational Gaussian approximation to the…

Numerical Analysis · Mathematics 2018-02-14 Simon Arridge , Kazufumi Ito , Bangti Jin , Chen Zhang

Accurate tuning of hyperparameters is crucial to ensure that models can generalise effectively across different settings. In this paper, we present theoretical guarantees for hyperparameter selection using variational Bayes in the…

Statistics Theory · Mathematics 2025-04-07 Dennis Nieman , Botond Szabó

A method is presented for the computation of the one-loop effective action at finite temperature and density. The method is based on an expansion in the number of spatial covariant derivatives. It applies to general background field…

High Energy Physics - Theory · Physics 2016-08-15 C. García-Recio , L. L. Salcedo

Variational inference techniques based on inducing variables provide an elegant framework for scalable posterior estimation in Gaussian process (GP) models. Besides enabling scalability, one of their main advantages over sparse…

Machine Learning · Statistics 2021-02-24 Simone Rossi , Markus Heinonen , Edwin V. Bonilla , Zheyang Shen , Maurizio Filippone

We revisit the replica method for analyzing inference and learning in parametric models, considering situations where the data-generating distribution is unknown or analytically intractable. Instead of assuming idealized distributions to…

Disordered Systems and Neural Networks · Physics 2025-11-17 Takashi Takahashi

An approximation method is presented for probabilistic inference with continuous random variables. These problems can arise in many practical problems, in particular where there are "second order" probabilities. The approximation, based on…

Artificial Intelligence · Computer Science 2013-04-10 Ross D. Shachter

We introduce a numerical method, based on finite elements and lattice gauge theory, to compute approximate solutions to Schr\"odinger and Pauli equations. The crucial geometric property of the method is discrete gauge invariance. The main…

Numerical Analysis · Mathematics 2015-06-01 Snorre Harald Christiansen , Tore Gunnar Halvorsen

We propose a gauge invariant formulation of the effective potential in terms of a gauge invariant order parameter, for the Abelian Higgs model. The one-loop contribution at zero and finite temperature is computed explicitly, and the leading…

High Energy Physics - Phenomenology · Physics 2014-11-17 D. Boyanovsky , D. Brahm , R. Holman , D. -S. Lee

A simple example is given of the implementation of the usual method of asymptotic expansions for weak gravitational fields. A scalar, preferred-frame theory of gravitation is considered, but the method is general. Two kinds of asymptotic…

General Relativity and Quantum Cosmology · Physics 2007-05-23 Mayeul Arminjon

This paper is devoted to the problem of sampling Gaussian fields in high dimension. Solutions exist for two specific structures of inverse covariance : sparse and circulant. The proposed approach is valid in a more general case and…

Computation · Statistics 2011-05-31 F. Orieux , O. Féron , J. -F. Giovannelli

In strongly coupled field theories, perturbation theory cannot be employed to study the low-energy spectrum. Thus, non-perturbative techniques are required. We employ the variational method, a rigorous, non-perturbative approach which…

High Energy Physics - Lattice · Physics 2024-09-27 M. Rovira , A. Parreño , R. J. Perry

The paper concerns the second-order generalized differentiation theory of variational analysis and new applications of this theory to some problems of constrained optimization in finitedimensional spaces. The main attention is paid to the…

Optimization and Control · Mathematics 2011-10-21 B. S. Mordukhovich , R. T. Rockafellar

Several numerical approximation strategies for the expectation-propagation algorithm are studied in the context of large-scale learning: the Laplace method, a faster variant of it, Gaussian quadrature, and a deterministic version of…

Computation · Statistics 2016-11-16 Alexis Roche

This paper introduces a new framework to study the asymptotical behavior of the empirical distribution function (e.d.f.) of Gaussian vector components, whose correlation matrix $\Gamma^{(m)}$ is dimension-dependent. Hence, by contrast with…

Statistics Theory · Mathematics 2013-05-07 Sylvain Delattre , Etienne Roquain

Interactions of gauge-invariant systems are severely constrained by several consistency requirements. One is the preservation of the number of gauge symmetries, another is causal propagation. For lower-spin fields, the emphasis is usually…

High Energy Physics - Theory · Physics 2013-09-11 Marc Henneaux , Rakibur Rahman

We present a Rayleigh-Schroedinger-Goldstone perturbation formalism for many fermion systems. Based on this formalism, variational perturbation scheme which goes beyond the Gaussian approximation is developed. In order to go beyond the…

Superconductivity · Physics 2009-11-10 Sang Koo You , Chul Koo Kim

We show how to use a variational approximation to the logistic function to perform approximate inference in Bayesian networks containing discrete nodes with continuous parents. Essentially, we convert the logistic function to a Gaussian,…

Artificial Intelligence · Computer Science 2013-01-30 Kevin Murphy

The first order form of a Maxwell theory and U(1) gauge theory in which a gauge invariant mass term appears is analyzed using the Dirac procedure. The form of the gauge transformation which leaves the action invariant is derived from the…

High Energy Physics - Theory · Physics 2015-06-03 N. Kiriushcheva , S. V. Kuzmin , D. G. C. McKeon