English
Related papers

Related papers: Mean-field Potts and random-cluster dynamics from …

200 papers

A curious phenomenon observed in some dynamical generative models is the following: despite learning errors in the score function or the drift vector field, the generated samples appear to shift \emph{along} the support of the data…

Machine Learning · Computer Science 2025-08-12 Nisha Chandramoorthy , Adriaan de Clercq

We prove two results on the mixing times of Markov chains for two-spin systems. First, we show that the Glauber dynamics mixes in polynomial time for the Gibbs distributions of antiferromagnetic two-spin systems at the critical threshold of…

Data Structures and Algorithms · Computer Science 2026-05-04 Xiaoyu Chen , Zhe Ju , Tianshun Miao , Yitong Yin , Xinyuan Zhang

In this paper, we develop a general theory for the estimation of the transition probabilities of reversible Markov chains using the maximum entropy principle. A broad range of physical models can be studied within this approach. We use…

Statistical Mechanics · Physics 2015-05-14 Erik Van der Straeten

Swendsen-Wang dynamics for the Potts model was proposed in the late 1980's as an alternative to single-site heat-bath dynamics, in which global updates allow this MCMC sampler to switch between metastable states and ideally mix faster. Gore…

Probability · Mathematics 2017-05-03 Reza Gheissari , Eyal Lubetzky , Yuval Peres

The spreading of entanglement in out-of-equilibrium quantum systems is currently at the centre of intense interdisciplinary research efforts involving communities with interests ranging from holography to quantum information. Here we…

Statistical Mechanics · Physics 2019-05-21 Bruno Bertini , Pavel Kos , Tomaz Prosen

In this paper, we study the evolution of tokens through the depth of encoder-only transformer models at inference time by modeling them as a system of particles interacting in a mean-field way and studying the corresponding dynamics. More…

Machine Learning · Computer Science 2025-09-30 Giuseppe Bruno , Federico Pasqualotto , Andrea Agazzi

The exact treatment of Markovian models of complex systems requires knowledge of probability distributions exponentially large in the number of components $n$. Mean-field approximations provide an effective reduction in complexity of the…

Statistical Mechanics · Physics 2025-03-12 Wout Merbis , Madelon Geurts , Clélia de Mulatier , Philippe Corboz

The partition function of the finite $1+\epsilon$ state Potts model is shown to yield a closed form for the distribution of clusters in the immediate vicinity of the percolation transition. Various important properties of the transition are…

Statistical Mechanics · Physics 2009-10-30 Joseph Rudnick , Paisan Nakmahachalasint , George Gaspari

The random-cluster model has been widely studied as a unifying framework for random graphs, spin systems and electrical networks, but its dynamics have so far largely resisted analysis. In this paper we analyze the Glauber dynamics of the…

Discrete Mathematics · Computer Science 2022-05-10 Antonio Blanca , Alistair Sinclair

We consider the performance of Glauber dynamics for the random cluster model with real parameter $q>1$ and temperature $\beta>0$. Recent work by Helmuth, Jenssen and Perkins detailed the ordered/disordered transition of the model on random…

Probability · Mathematics 2025-04-30 Andreas Galanis , Leslie Ann Goldberg , Paulina Smolarova

We study the speed of convergence of the Swendsen-Wang (SW) dynamics for the $q$-state ferromagnetic Potts model on the $n$-vertex complete graph, known as the mean-field model. The SW dynamics was introduced as an attractive alternative to…

Probability · Mathematics 2025-10-14 Antonio Blanca , Zhezheng Song

Simple models of infectious diseases tend to assume random mixing of individuals, but real interactions are not random pairwise encounters: they occur within various types of gatherings such as workplaces, households, schools, and concerts,…

We study the mixing time of the Swendsen-Wang dynamics for the ferromagnetic Ising and Potts models on the integer lattice ${\mathbb Z}^d$. This dynamics is a widely used Markov chain that has largely resisted sharp analysis because it is…

Probability · Mathematics 2021-03-25 Antonio Blanca , Pietro Caputo , Daniel Parisi , Alistair Sinclair , Eric Vigoda

Minimization of the (regularized) entropy of classification probabilities is a versatile class of discriminative clustering methods. The classification probabilities are usually defined through the use of some classical losses from…

Statistics Theory · Mathematics 2021-12-17 Edouard Genetay , Adrien Saumard , Rémi Coulaud

We study the $q$-state ferromagnetic Potts model on the $n$-vertex complete graph known as the mean-field (Curie-Weiss) model. We analyze the Swendsen-Wang algorithm which is a Markov chain that utilizes the random cluster representation…

Discrete Mathematics · Computer Science 2017-11-27 Andreas Galanis , Daniel Stefankovic , Eric Vigoda

The evolution of tokens through deep transformer models can be modeled as an interacting particle system that has been shown to exhibit an asymptotic clustering behavior akin to the synchronization phenomenon in Kuramoto models. In this…

Machine Learning · Computer Science 2026-05-12 Shi Chen , Zhengjiang Lin , Yury Polyanskiy , Philippe Rigollet

In the past few years, deep generative models, such as generative adversarial networks \autocite{GAN}, variational autoencoders \autocite{vaepaper}, and their variants, have seen wide adoption for the task of modelling complex data…

Machine Learning · Statistics 2020-09-02 Guilherme G. P. Freitas Pires , Mário A. T. Figueiredo

Clustering is a fundamental tool in statistical machine learning in the presence of heterogeneous data. Most recent results focus primarily on optimal mislabeling guarantees when data are distributed around centroids with sub-Gaussian…

Statistics Theory · Mathematics 2024-10-24 Soham Jana , Jianqing Fan , Sanjeev Kulkarni

We consider the Potts model on a two-dimensional periodic rectangular lattice with general coupling constants $J_{ij}>0$, where $i,j\in\{1,2,3\}$ are the possible spin values (or colors). The resulting energy landscape is thus significantly…

Probability · Mathematics 2024-05-09 Gianmarco Bet , Anna Gallo , Seonwoo Kim

In this paper, we explore the metastable behavior of the Glauber dynamics associated with the three-state Potts model with an asymmetrical external field at a low-temperature regime. The model exhibits three monochromatic configurations: a…

Probability · Mathematics 2023-11-17 Jeonghyun Ahn