English
Related papers

Related papers: Metastable Mixing of Markov Chains: Efficiently Sa…

200 papers

Estimating the entropy based on data is one of the prototypical problems in distribution property testing and estimation. For estimating the Shannon entropy of a distribution on $S$ elements with independent samples, [Paninski2004] showed…

Machine Learning · Computer Science 2018-09-25 Yanjun Han , Jiantao Jiao , Chuan-Zheng Lee , Tsachy Weissman , Yihong Wu , Tiancheng Yu

We address the problem of estimating the mixing time of a Markov chain from a single trajectory of observations. Unlike most previous works which employed Hilbert space methods to estimate spectral gaps, we opt for an approach based on…

Probability · Mathematics 2023-09-13 Geoffrey Wolfer

We provide a general framework for computing upper bounds on mixing times of finite Markov chains when its minimal ideal is left zero. Our analysis is based on combining results by Brown and Diaconis with our previous work on stationary…

Probability · Mathematics 2023-01-04 John Rhodes , Anne Schilling

The maximum independent set (MIS) problem is a well-studied combinatorial optimization problem that naturally arises in many applications, such as wireless communication, information theory and statistical mechanics. MIS problem is NP-hard,…

Discrete Mathematics · Computer Science 2015-04-20 Rémi Varloot , Ana Bušić , Anne Bouillard

Consider random $d$-regular graphs, i.e., random graphs such that there are exactly $d$ edges from each vertex for some $d\ge 3$. We study both the configuration model version of this graph, which has occasional multi-edges and self-loops,…

Probability · Mathematics 2021-04-27 Van Hao Can , Remco van der Hofstad , Takashi Kumagai

Motivated by the community detection problem in Bayesian inference, as well as the recent explosion of interest in spin glasses from statistical physics, we study the classical Glauber dynamics for sampling from Ising models with sparse…

Probability · Mathematics 2024-08-07 Kuikui Liu , Sidhanth Mohanty , Amit Rajaraman , David X. Wu

Gibbs sampling is a Markov chain Monte Carlo technique commonly used for estimating marginal distributions. To speed up Gibbs sampling, there has recently been interest in parallelizing it by executing asynchronously. While empirical…

Machine Learning · Computer Science 2016-06-20 Christopher De Sa , Kunle Olukotun , Christopher Ré

We investigate the mixing properties of a model of reversible Markov chains in random environment, which notably contains the simple random walk on the superposition of a deterministic graph and a second graph whose vertex set has been…

Probability · Mathematics 2026-05-13 Bastien Dubail

In this paper we consider the convergence of the conditional entropy to the entropy rate for Markov chains. Convergence of certain statistics of long range dependent processes, such as the sample mean, is slow. It has been shown in Carpio…

Probability · Mathematics 2021-10-29 Andrew Feutrill , Matthew Roughan

We consider the problem of sampling from the ferromagnetic Potts and random-cluster models on a general family of random graphs via the Glauber dynamics for the random-cluster model. The random-cluster model is parametrized by an edge…

Probability · Mathematics 2023-02-28 Antonio Blanca , Reza Gheissari

We study the single-site Glauber dynamics for the fugacity $\lambda$, Hard-core model on the random graph $G(n, d/n)$. We show that for the typical instances of the random graph $G(n,d/n)$ and for fugacity $\lambda <…

Discrete Mathematics · Computer Science 2023-02-14 Charilaos Efthymiou , Weiming Feng

We define a general class of network formation models, Statistical Exponential Random Graph Models (SERGMs), that nest standard exponential random graph models (ERGMs) as a special case. We provide the first general results on when these…

Physics and Society · Physics 2014-06-26 Arun G. Chandrasekhar , Matthew O. Jackson

Exponential random graph models (ERGMs) are very flexible for modeling network formation but pose difficult estimation challenges due to their intractable normalizing constant. Existing methods, such as MCMC-MLE, rely on sequential…

Social and Information Networks · Computer Science 2025-02-05 Angelo Mele

In this article, we study the mixing properties of metastable diffusion processes which possess a Gibbs invariant distribution. For systems with multiple stable equilibria, so-called metastable transitions between these equilibria are…

Probability · Mathematics 2025-04-29 Jungkyoung Lee

Lifted Markov chains are Markov chains on graphs with added local "memory" and can be used to mix towards a target distribution faster than their memoryless counterparts. Upper and lower bounds on the achievable performance have been…

Optimization and Control · Mathematics 2017-05-24 Simon Apers , Francesco Ticozzi , Alain Sarlette

We explore the cooperative behaviour and phase transitions of interacting networks by studying a simplified model consisting of Ising spins placed on the nodes of two coupled Erd\"os-R\'enyi random graphs. We derive analytical expressions…

Statistical Mechanics · Physics 2018-08-27 Maíra Bolfe , Lucas Nicolao , Fernando L. Metz

We study the stochastic Ising model on finite graphs with n vertices and bounded degree and analyze the effect of boundary conditions on the mixing time. We show that for all low enough temperatures, the spectral gap of the dynamics with…

Probability · Mathematics 2008-11-10 Alessandra Bianchi

Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iterating short forward-backward steps of a diffusion model, in which each step proposes a…

Machine Learning · Computer Science 2026-05-27 Hyunmo Kang , Noam Itzhak Levi , Corinna Elena Wegner , Daniel J. Korchinski , Matthieu Wyart

We introduce a framework for obtaining tight mixing times for Markov chains based on what we call restricted modified log-Sobolev inequalities. Modified log-Sobolev inequalities (MLSI) quantify the rate of relative entropy contraction for…

Data Structures and Algorithms · Computer Science 2021-11-08 Nima Anari , Vishesh Jain , Frederic Koehler , Huy Tuan Pham , Thuy-Duong Vuong

Restricted Boltzmann Machines (RBM) have attracted a lot of attention of late, as one the principle building blocks of deep networks. Training RBMs remains problematic however, because of the intractibility of their partition function. The…

Machine Learning · Statistics 2010-12-17 Guillaume Desjardins , Aaron Courville , Yoshua Bengio
‹ Prev 1 4 5 6 7 8 10 Next ›