English
Related papers

Related papers: Learning of Statistical Field Theories

200 papers

We propose a novel approach to the inverse Ising problem which employs the recently introduced Density Consistency approximation (DC) to determine the model parameters (couplings and external fields) maximizing the likelihood of given…

Statistical Mechanics · Physics 2021-04-01 Alfredo Braunstein , Giovanni Catania , Luca Dall'Asta , Anna Paola Muntoni

We propose to solve inverse problems involving the temporal evolution of physics systems by leveraging recent advances from diffusion models. Our method moves the system's current state backward in time step by step by combining an…

Machine Learning · Computer Science 2023-12-06 Benjamin J. Holzschuh , Simona Vegetti , Nils Thuerey

Inverse statistical physics aims at inferring models compatible with a set of empirical averages estimated from a high-dimensional dataset of independently distributed equilibrium configurations of a given system. However, in several…

Disordered Systems and Neural Networks · Physics 2021-02-12 Edwin Rodriguez Horta , Alejandro Lage , Martin Weigt , Pierre Barrat-Charlaix

Learning Gibbs distributions using only sufficient statistics has long been recognized as a computationally hard problem. On the other hand, computationally efficient algorithms for learning Gibbs distributions rely on access to full sample…

Machine Learning · Computer Science 2026-02-16 Abhijith Jayakumar , Shreya Shukla , Marc Vuffray , Andrey Y. Lokhov , Sidhant Misra

We investigate the learning performance of the pseudolikelihood maximization method for inverse Ising problems. In the teacher-student scenario under the assumption that the teacher's couplings are sparse and the student does not know the…

Disordered Systems and Neural Networks · Physics 2020-08-26 Alia Abbara , Yoshiyuki Kabashima , Tomoyuki Obuchi , Yingying Xu

Statistical inverse learning aims at recovering an unknown function $f$ from randomly scattered and possibly noisy point evaluations of another function $g$, connected to $f$ via an ill-posed mathematical model. In this paper we blend…

Statistics Theory · Mathematics 2024-01-22 Tapio Helin

In these notes the exact renormalization group formulation of the scalar theory is briefly reviewed. This regularization scheme is then applied to supersymmetric theories. In case of a supersymmetric gauge theory it is also shown how to…

High Energy Physics - Theory · Physics 2007-05-23 Federica Vian

One challenge of physics is to explain how collective properties arise from microscopic interactions. Indeed, interactions form the building blocks of almost all physical theories and are described by polynomial terms in the action. The…

Disordered Systems and Neural Networks · Physics 2023-05-03 Claudia Merger , Alexandre René , Kirsten Fischer , Peter Bouss , Sandra Nestler , David Dahmen , Carsten Honerkamp , Moritz Helias

Recovering a low-complexity signal from its noisy observations by regularization methods is a cornerstone of inverse problems and compressed sensing. Stable recovery ensures that the original signal can be approximated linearly by optimal…

Optimization and Control · Mathematics 2025-05-30 Tran T. A. Nghia , Huy N. Pham , Nghia V. Vo

Linear problems appear in a variety of disciplines and their application for the transmission matrix recovery is one of the most stimulating challenges in biomedical imaging. Its knowledge turns any random media into an optical tool that…

Machine Learning · Statistics 2019-02-05 Daniele Ancora , Luca Leuzzi

In recent years, with the increase in renewable energy and storage penetration, power flow studies in low-voltage networks have become of interest in both industry and academia. Many studies use impedance represented by sequence components…

Optimization and Control · Mathematics 2025-06-10 Ching Hong Tam , Frederik Geth , Nadarajah Mithulananthan

We address the inverse problem of reconstructing both the structure and dynamics of a network from mean-field measurements, which are linear combinations of node states. This setting arises in applications where only a few aggregated…

Dynamical Systems · Mathematics 2025-11-04 Narcicegi Kiran , Tiago Pereira

The support recovery problem consists of determining a sparse subset of a set of variables that is relevant in generating a set of observations, and arises in a diverse range of settings such as compressive sensing, and subset selection in…

Information Theory · Computer Science 2016-08-31 Jonathan Scarlett , Volkan Cevher

Inference and learning of graphical models are both well-studied problems in statistics and machine learning that have found many applications in science and engineering. However, exact inference is intractable in general graphical models,…

Machine Learning · Statistics 2015-02-04 Jason K. Johnson , Diane Oyen , Michael Chertkov , Praneeth Netrapalli

Inferring a generative model from data is a fundamental problem in machine learning. It is well-known that the Ising model is the maximum entropy model for binary variables which reproduces the sample mean and pairwise correlations.…

Statistical Mechanics · Physics 2018-06-19 Soma Turi , Alpha A. Lee

We introduce in this document a direct method allowing to solve numerically inverse type problems for linear parabolic equations. We consider the reconstruction of the full solution of the parabolic equation posed in $\Omega\times (0,T)$ -…

Optimization and Control · Mathematics 2024-02-11 Arnaud Munch , Diego Souza

In an era of unprecedented deluge of (mostly unstructured) data, graphs are proving more and more useful, across the sciences, as a flexible abstraction to capture complex relationships between complex objects. One of the main challenges…

Disordered Systems and Neural Networks · Physics 2016-10-17 Alaa Saade

We study the inverse problem of deducing the dynamical characteristics (such as the potential field) of large systems from kinematic observations. We show that, for a class of steady-state systems, the solution is unique even with…

Astrophysics · Physics 2008-11-14 Mikko Kaasalainen

We propose a general framework for solving statistical mechanics of systems with finite size. The approach extends the celebrated variational mean-field approaches using autoregressive neural networks, which support direct sampling and…

Statistical Mechanics · Physics 2019-06-10 Dian Wu , Lei Wang , Pan Zhang

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