English
Related papers

Related papers: A statistical mechanics approach to Granovetter th…

200 papers

This paper presents a theoretical convergence analysis for an opinion-action coevolution model that integrates the opinion updating rule of the Hegselmann-Krause model with a utility-based decision-making mechanism. The model is…

Systems and Control · Electrical Eng. & Systems 2026-04-08 Chen Song , Angela Fontan , Rong Su , Julien M. Hendrickx , Vladimir Cvetkovic , Karl H. Johansson

We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically. We develop a…

Machine Learning · Statistics 2018-07-03 John Duchi , Peter Glynn , Hongseok Namkoong

We propose a novel method to directly learn a stochastic transition operator whose repeated application provides generated samples. Traditional undirected graphical models approach this problem indirectly by learning a Markov chain model…

Machine Learning · Statistics 2017-11-08 Anirudh Goyal , Nan Rosemary Ke , Surya Ganguli , Yoshua Bengio

This paper is a review of results which have been recently obtained by applying mathematical concepts drawn, in particular, from differential geometry and topology, to the physics of Hamiltonian dynamical systems with many degrees of…

Statistical Mechanics · Physics 2009-10-31 Lapo Casetti , Marco Pettini , E. G. D. Cohen

Despite substantial progress in non-equilibrium physics, steady-state (s.s.) probabilities remain intractable to analysis. For a Markov process, s.s. probabilities can be expressed in terms of transition rates using the Matrix-Tree theorem…

Statistical Mechanics · Physics 2021-09-07 Ugur Cetiner , Jeremy Gunawardena

Scharfstein et al. (2021) developed a sensitivity analysis model for analyzing randomized trials with repeatedly measured binary outcomes that are subject to nonmonotone missingness. Their approach becomes computationally intractable when…

We develop an information-theoretic formulation of stochastic dynamics in which the fundamental stochastic variable is the total action connecting spacetime points, rather than individual paths. By maximizing Shannon entropy over a joint…

We study the family of network models derived by requiring the expected properties of a graph ensemble to match a given set of measurements of a real-world network, while maximizing the entropy of the ensemble. Models of this type play the…

Statistical Mechanics · Physics 2009-11-10 Juyong Park , M. E. J. Newman

Graphical models are commonly used to represent conditional dependence relationships between variables. There are multiple methods available for exploring them from high-dimensional data, but almost all of them rely on the assumption that…

Machine Learning · Statistics 2020-04-22 Tianxi Li , Cheng Qian , Elizaveta Levina , Ji Zhu

Starting at the mesoscopic level with a general formulation of stochastic thermodynamics in terms of Markov jump processes, we identify the scaling conditions that ensure the emergence of a (typically nonlinear) deterministic dynamics and…

Statistical Mechanics · Physics 2025-05-26 Gianmaria Falasco , Massimiliano Esposito

We propose a modification of the cost function of the Hopfield model whose salient features shine in its Taylor expansion and result in more than pairwise interactions with alternate signs, suggesting a unified framework for handling both…

Disordered Systems and Neural Networks · Physics 2018-01-08 Adriano Barra , Matteo Beccaria , Alberto Fachechi

We build on the foundational work of Deffner and Zurek [S. Deffner and W. H. Zurek, New J. Phys. 18, 063013 (2016)] to show how central equilibrium structures of statistical mechanics can be understood within standard quantum mechanics…

Quantum Physics · Physics 2026-04-22 Amul Ojha , Shubhit Sardana , Arnab Ghosh

Neural dynamics of energy-based models are governed by energy minimization and the patterns stored in the network are retrieved when the system reaches equilibrium. However, when the system is driven by time-varying external input, the…

Neurons and Cognition · Quantitative Biology 2020-12-25 Kevin S. Chen

Statistical mechanics explains the properties of macroscopic phenomena based on the movements of microscopic particles such as atoms and molecules. Movements of microscopic particles can be represented by large-scale interacting systems. In…

Probability · Mathematics 2026-04-15 Kenichi Bannai , Jun Koriki , Makiko Sasada , Hidetada Wachi , Shuji Yamamoto

Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging. Standard approaches often rely on short-time…

Machine Learning · Statistics 2026-04-28 Ludovico T. Giorgini

We provide solid evidence for the long-standing presumption that model Hamiltonians with short-range interactions faithfully reproduce the physics of the long-range Coulomb interaction in real materials. For this aim, we address a generic…

Strongly Correlated Electrons · Physics 2025-06-09 Florian Gebhard , Kevin Bauerbach , Örs Legeza

The analysis of practical probabilistic models on the computer demands a convenient representation for the available knowledge and an efficient algorithm to perform inference. An appealing representation is the influence diagram, a network…

Artificial Intelligence · Computer Science 2013-04-15 Ross D. Shachter

We study the Hopfield model on a random graph in scaling regimes where the average number of connections per neuron is a finite number and where the spin dynamics is governed by a synchronous execution of the microscopic update rule…

Condensed Matter · Physics 2016-08-16 I. Pérez Castillo , N. S. Skantzos

For most people, social contacts play an integral part in finding a new job. As observed by Granovetter's seminal study, the proportion of jobs obtained through social contacts is usually large compared to those obtained through postings or…

Computer Science and Game Theory · Computer Science 2009-10-07 Esteban Arcaute , Sergei Vassilvitskii

Model reduction of Markov processes is a basic problem in modeling state-transition systems. Motivated by the state aggregation approach rooted in control theory, we study the statistical state compression of a discrete-state Markov chain…

Machine Learning · Statistics 2019-11-26 Anru Zhang , Mengdi Wang