English
Related papers

Related papers: Learning the Sherrington-Kirkpatrick Model Even at…

200 papers

We train a set of Restricted Boltzmann Machines (RBMs) on one- and two-dimensional Ising spin configurations at various values of temperature, generated using Monte Carlo simulations. We validate the training procedure by monitoring several…

Computational Physics · Physics 2019-08-14 Guido Cossu , Luigi Del Debbio , Tommaso Giani , Ava Khamseh , Michael Wilson

We study a spin system with both mixed even-spin Sherrington-Kirkpatrick (SK) couplings and Curie-Weiss (CW) interaction. Our main results are: (i) The thermodynamic limit of the free energy is given by a variational formula involving the…

Probability · Mathematics 2012-12-03 Wei-Kuo Chen

In this paper, we study the problem of inferring time-varying Markov random fields (MRF), where the underlying graphical model is both sparse and changes sparsely over time. Most of the existing methods for the inference of time-varying…

Machine Learning · Computer Science 2021-02-09 Salar Fattahi , Andres Gomez

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies…

Artificial Intelligence · Computer Science 2016-04-14 Michael Herman , Tobias Gindele , Jörg Wagner , Felix Schmitt , Wolfram Burgard

Machine learning (ML) techniques, especially neural networks (NNs), have shown promise in learning subgrid-scale parameterizations for climate models. However, a major problem with data-driven parameterizations, particularly those learned…

Atmospheric and Oceanic Physics · Physics 2024-07-17 Hamid A. Pahlavan , Pedram Hassanzadeh , M. Joan Alexander

Reward modeling is not only a prediction problem: in KL-regularized policy optimization, the learned reward is exponentiated to define the deployed policy, so downstream value depends on errors in reward-tilted regions. We study this…

Machine Learning · Statistics 2026-05-26 Rei Higuchi , Ryotaro Kawata , Akifumi Wachi , Shokichi Takakura , Kohei Miyaguchi , Taiji Suzuki

We study the metastability of the ferromagnetic Ising model on a random $r$-regular graph in the zero temperature limit. We prove that in the presence of a small positive external field the time that it takes to go from the all minus state…

Probability · Mathematics 2015-11-23 Sander Dommers

We present a new approach to a classical problem in statistical physics: estimating the partition function and other thermodynamic quantities of the ferromagnetic Ising model. Markov chain Monte Carlo methods for this problem have been…

Statistical Mechanics · Physics 2013-06-20 Amanda Streib , Noah Streib , Isabel Beichl , Francis Sullivan

We study the performance and convergence properties of the Susceptibility Propagation (SusP) algorithm for solving the Inverse Ising problem. We first study how the temperature parameter (T) in a Sherrington-Kirkpatrick model generating the…

Disordered Systems and Neural Networks · Physics 2010-10-01 Erik Aurell , Charles Ollion , Yasser Roudi

Temperature monitoring during the life time of heat source components in engineering systems becomes essential to guarantee the normal work and the working life of these components. However, prior methods, which mainly use the interpolate…

Machine Learning · Computer Science 2022-12-27 Zhiqiang Gong , Weien Zhou , Jun Zhang , Wei Peng , Wen Yao

We study numerically the Sherrington--Kirkpatrick model as function of the magnetic field h, with fixed temperature T=0.6 Tc. We investigate the finite size scaling behavior of several quantities, such as the spin glass susceptibility,…

Statistical Mechanics · Physics 2009-11-10 Alain Billoire , Barbara Coluzzi

Recent advances in deep learning and neural networks have led to an increased interest in the application of generative models in statistical and condensed matter physics. In particular, restricted Boltzmann machines (RBMs) and variational…

Disordered Systems and Neural Networks · Physics 2020-06-09 Francesco D'Angelo , Lucas Böttcher

Bayesian learning in undirected graphical models|computing posterior distributions over parameters and predictive quantities is exceptionally difficult. We conjecture that for general undirected models, there are no tractable MCMC (Markov…

Machine Learning · Computer Science 2012-07-19 Iain Murray , Zoubin Ghahramani

We investigate the parameter space of transformer models trained on protein sequence data using a statistical mechanics framework, sampling the loss landscape at varying temperatures by Langevin dynamics to characterize the low-loss…

Disordered Systems and Neural Networks · Physics 2026-04-01 L. Ghiringhelli , A. Zambon , G. Tiana

The ferromagnetic Ising model is a model of a magnetic material and a central topic in statistical physics. It also plays a starring role in the algorithmic study of approximate counting: approximating the partition function of the…

Data Structures and Algorithms · Computer Science 2021-11-05 Charlie Carlson , Ewan Davies , Alexandra Kolla , Will Perkins

Consider the problem of joint parameter estimation and prediction in a Markov random field: i.e., the model parameters are estimated on the basis of an initial set of data, and then the fitted model is used to perform prediction (e.g.,…

Machine Learning · Computer Science 2007-07-13 Martin J. Wainwright

The large amounts of data from molecular biology and neuroscience have lead to a renewed interest in the inverse Ising problem: how to reconstruct parameters of the Ising model (couplings between spins and external fields) from a number of…

Disordered Systems and Neural Networks · Physics 2012-08-13 H. Chau Nguyen , Johannes Berg

Land surface temperature (LST) retrieval from remote sensing data is pivotal for analyzing climate processes and surface energy budgets. However, LST retrieval is an ill-posed inverse problem, which becomes particularly severe when only a…

Atmospheric and Oceanic Physics · Physics 2026-03-18 Tian Xie , Menghui Jiang , Huanfeng Shen , Huifang Li , Chao Zeng , Jun Ma , Guanhao Zhang , Liangpei Zhang

The infinite-range-interaction Ising spin glass is considered in the presence of an external random magnetic field following a trimodal (three-peak) distribution. The model is studied through the replica method and phase diagrams are…

Statistical Mechanics · Physics 2009-10-31 J. M. de Araujo , F. D. Nobre , F. A. da Costa

Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function and its derivatives. Here we propose a new parameter estimation technique that does not require computing an intractable…

Machine Learning · Computer Science 2015-03-13 Jascha Sohl-Dickstein , Peter Battaglino , Michael R. DeWeese