English
Related papers

Related papers: Group-averaged Markov chains: mixing improvement

200 papers

Spectral methods have proven to be a highly effective tool in understanding the intrinsic geometry of a high-dimensional data set $\left\{x_i \right\}_{i=1}^{n} \subset \mathbb{R}^d$. The key ingredient is the construction of a Markov chain…

Discrete Mathematics · Computer Science 2014-11-07 Stefan Steinerberger

Kernel smoothing is a widely used nonparametric method in modern statistical analysis. The problem of efficiently conducting kernel smoothing for a massive dataset on a distributed system is a problem of great importance. In this work, we…

Computation · Statistics 2024-10-08 Yuan Gao , Rui Pan , Feng Li , Riquan Zhang , Hansheng Wang

This paper proposes a new type of recurrence where we divide the Markov chains into intervals that start when the chain enters into a subset A, then sample another subset B far away from A and end when the chain again return to A. The…

Methodology · Statistics 2016-02-24 Lars Holden

With view to applications, we here give an explicit correspondence between the following two: (i) the set of symmetric and positive measures $\rho$ on one hand, and (ii) a certain family of generalized Markov transition measures $P$, with…

Functional Analysis · Mathematics 2018-12-04 Sergey Bezuglyi , Palle E. T. Jorgensen

We analyze the general biased adjacent transposition shuffle process, which is a well-studied Markov chain on the symmetric group $S_n$. In each step, an adjacent pair of elements $i$ and $j$ are chosen, and then $i$ is placed ahead of $j$…

Probability · Mathematics 2025-11-05 Reza Gheissari , Holden Lee , Eric Vigoda

Given a partial action $\alpha$ of a groupoid $G$ on a ring $R$, we study the associated partial skew groupoid ring $R \rtimes_{\alpha} G$, which carries a natural $G$-grading. We show that there is a one-to-one correspondence between the…

Rings and Algebras · Mathematics 2022-12-15 Dirceu Bagio , Daniel Gonçalves , Paula Savana Estácio Moreira , Johan Öinert

Many natural Markov chains fail to mix to their stationary distribution in polynomially many steps. Often, this slow mixing is inevitable since it is computationally intractable to sample from their stationary measure. Nevertheless, Markov…

Data Structures and Algorithms · Computer Science 2025-07-08 Kuikui Liu , Sidhanth Mohanty , Prasad Raghavendra , Amit Rajaraman , David X. Wu

The Robust Perron Cluster Analysis (PCCA+) has become a popular spectral clustering algorithm for coarse-graining transition matrices of nearly decomposable Markov chains with transition states. Originally developed for reversible Markov…

Methodology · Statistics 2022-08-19 Anna-Simone Frank , Alexander Sikorski , Susanna Röblitz

Stochastic kernel based dimensionality reduction approaches have become popular in the last decade. The central component of many of these methods is a symmetric kernel that quantifies the vicinity between pairs of data points and a…

Machine Learning · Computer Science 2018-08-08 Purushottam D. Dixit

Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature…

Machine Learning · Statistics 2022-06-14 Bharath Sriperumbudur , Nicholas Sterge

We consider a pseudo-marginal Metropolis--Hastings kernel $P_m$ that is constructed using an average of $m$ exchangeable random variables, as well as an analogous kernel $P_s$ that averages $s<m$ of these same random variables. Using an…

Methodology · Statistics 2016-11-01 Chris Sherlock , Alexandre Thiery , Anthony Lee

When two Markov operators commute, it suggests that we can couple two copies of one of the corresponding processes. We explicitly construct a number of couplings of this type for a commuting family of Markov processes on the set of…

Probability · Mathematics 2008-11-20 Anthony P. Metcalfe , Neil O'Connell , Jon Warren

Specialized classifiers, namely those dedicated to a subset of classes, are often adopted in real-world recognition systems. However, integrating such classifiers is nontrivial. Existing methods, e.g. weighted average, usually implicitly…

Machine Learning · Computer Science 2017-09-08 Zhizhong Li , Dahua Lin

The purpose of this paper is to study the time average behavior of Markov chains with transition probabilities being kernels of completely continuous operators, and therefore to provide a sufficient condition for a class of Markov chains…

Probability · Mathematics 2018-11-16 Shizhou Xu

We study the problem of clustering $T$ trajectories of length $H$, each generated by one of K unknown ergodic Markov chains over a finite state space of size $S$. We derive an instance-dependent, high-probability lower bound on the…

Machine Learning · Statistics 2026-03-18 Junghyun Lee , Yassir Jedra , Alexandre Proutière , Se-Young Yun

We argue that the spectral theory of non-reversible Markov chains may often be more effectively cast within the framework of the naturally associated weighted-$L_\infty$ space $L_\infty^V$, instead of the usual Hilbert space $L_2=L_2(\pi)$,…

Probability · Mathematics 2009-06-30 Ioannis Kontoyiannis , Sean P. Meyn

Suppose that $\gamma$ and $\sigma$ are two continuous bounded variation paths which take values in a finite-dimensional inner product space $V$. Recent papers have introduced the truncated and the untruncated signature kernel of $\gamma$…

Probability · Mathematics 2024-02-06 Thomas Cass , Terry Lyons , Xingcheng Xu

We study normal approximations for a class of discrete-time occupancy processes, namely, Markov chains with transition kernels of product Bernoulli form. This class encompasses numerous models which appear in the complex networks…

Probability · Mathematics 2018-11-13 Liam Hodgkinson , Ross McVinish , Philip K. Pollett

Markov chains are a class of probabilistic models that have achieved widespread application in the quantitative sciences. This is in part due to their versatility, but is compounded by the ease with which they can be probed analytically.…

Machine Learning · Computer Science 2023-12-18 Eddie Seabrook , Laurenz Wiskott

We present in this work a new family of kernels to compare positive measures on arbitrary spaces $\Xcal$ endowed with a positive kernel $\kappa$, which translates naturally into kernels between histograms or clouds of points. We first cover…

Machine Learning · Statistics 2009-09-08 Marco Cuturi
‹ Prev 1 3 4 5 6 7 10 Next ›