English
Related papers

Related papers: Wilsonian Renormalization of Neural Network Gaussi…

200 papers

Gaussian processes (GPs) are Bayesian nonparametric generative models that provide interpretability of hyperparameters, admit closed-form expressions for training and inference, and are able to accurately represent uncertainty. To model…

Machine Learning · Statistics 2018-03-21 Gonzalo Rios , Felipe Tobar

The Wilsonian renormalization group (RG) requires Euclidean signature. The conformal factor of the metric then has a wrong-sign kinetic term, which has a profound effect on its RG properties. Generically for the conformal sector, complete…

High Energy Physics - Theory · Physics 2018-08-10 Tim R. Morris

Renormalisation group (RG) methods provide one of the most important techniques for analysing the physics of many-body systems, both analytically and numerically. By iterating an RG map, which "course-grains" the description of a many-body…

Quantum Physics · Physics 2022-12-26 James D. Watson , Emilio Onorati , Toby S. Cubitt

The key idea behind the renormalization group (RG) transformation is that properties of physical systems with very different microscopic makeups can be characterized by a few universal parameters. However, finding the optimal RG…

Disordered Systems and Neural Networks · Physics 2021-06-30 Jui-Hui Chung , Ying-Jer Kao

Flow-based generative models have become an important class of unsupervised learning approaches. In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution to design a hierarchical flow-based…

Machine Learning · Computer Science 2022-08-16 Hong-Ye Hu , Dian Wu , Yi-Zhuang You , Bruno Olshausen , Yubei Chen

This paper presents a new approach to a robust Gaussian process (GP) regression. Most existing approaches replace an outlier-prone Gaussian likelihood with a non-Gaussian likelihood induced from a heavy tail distribution, such as the…

Machine Learning · Computer Science 2020-01-15 Chiwoo Park , David J. Borth , Nicholas S. Wilson , Chad N. Hunter , Fritz J. Friedersdorf

The Gaussian process (GP) regression can be severely biased when the data are contaminated by outliers. This paper presents a new robust GP regression algorithm that iteratively trims the most extreme data points. While the new algorithm…

Machine Learning · Computer Science 2021-06-15 Zhao-Zhou Li , Lu Li , Zhengyi Shao

We present a unified framework for the renormalisation of the Hamiltonian and eigenbasis of a system of correlated electrons, unveiling thereby the interplay between electronic correlations and many-particle entanglement. For this, we…

Strongly Correlated Electrons · Physics 2021-10-25 Anirban Mukherjee , Siddhartha Lal

The gradient flow bears a close resemblance to the coarse graining, the guiding principle of the renormalization group (RG). In the case of scalar field theory, a precise connection has been made between the gradient flow and the RG flow of…

High Energy Physics - Theory · Physics 2021-03-10 Hidenori Sonoda , Hiroshi Suzuki

We introduce the use of autoregressive normalizing flows for rapid likelihood-free inference of binary black hole system parameters from gravitational-wave data with deep neural networks. A normalizing flow is an invertible mapping on a…

Instrumentation and Methods for Astrophysics · Physics 2020-11-25 Stephen R. Green , Christine Simpson , Jonathan Gair

Renormalization Group (RG) techniques have been successfully employed in quantum field theory and statistical physics. Here we apply RG methods to study the non-linear stages of structure formation in the Universe. Exact equations for the…

Astrophysics · Physics 2010-10-27 Sabino Matarrese , Massimo Pietroni

In the context of Wilsonian Renormalization, renormalization group (RG) flows are a set of differential equations that defines how the coupling constants of a theory depend on an energy scale. These equations closely resemble…

High Energy Physics - Theory · Physics 2021-06-18 Caio Luiz Tiedt

Angular data are commonly encountered in settings with a directional or orientational component. Regressing an angular response on real-valued features requires intrinsically capturing the circular or spherical manifold the data lie on, or…

We investigate non-Abelian gauge theories within a Wilsonian Renormalisation Group approach. Our main question is: How close can one get to a gauge invariant flow, despite the fact that a Wilsonian coarse-graining seems to be incompatible…

High Energy Physics - Theory · Physics 2007-05-23 Daniel F. Litim , Jan M. Pawlowski

Some recent results showed that renormalization group can be considered as a promising framework to address open issues in data analysis. In this work, we focus on one of these aspects, closely related to principal component analysis for…

High Energy Physics - Theory · Physics 2022-03-04 Vincent Lahoche , Dine Ousmane Samary , Mohamed Tamaazousti

Gaussian processes (GPs) are ubiquitous tools for modeling and predicting continuous processes in physical and engineering sciences. This is partly due to the fact that one may employ a Gaussian process as an interpolator while facilitating…

Statistics Theory · Mathematics 2025-12-16 D. Andrew Brown , Peter Kiessler , John Nicholson

Kernel ridge regression (KRR) and Gaussian processes (GPs) are fundamental tools in statistics and machine learning, with recent applications to highly over-parameterized deep neural networks. The ability of these tools to learn a target…

Machine Learning · Statistics 2025-02-18 Itay Lavie , Zohar Ringel

Functional Renormalization Group Equations constitute a powerful tool to encode the perturbative and non-perturbative properties of a physical system. We present an algorithm to systematically compute the expansion of such flow equations in…

High Energy Physics - Theory · Physics 2011-06-23 Dario Benedetti , Kai Groh , Pedro F. Machado , Frank Saueressig

Gaussian Process (GP) models are a powerful tool in probabilistic machine learning with a solid theoretical foundation. Thanks to current advances, modeling complex data with GPs is becoming increasingly feasible, which makes them an…

Machine Learning · Computer Science 2025-03-04 Sarem Seitz

We develop a Renormalization Group (RG) approach to the study of existence and uniqueness of solutions to stochastic partial differential equations driven by space-time white noise. As an example we prove well-posedness and independence of…

Probability · Mathematics 2015-02-20 Antti Kupiainen