Kapak Resmi

Marathon: An Open Source Software Library for the Analysis of Markov-Chain Monte Carlo Algorithms

Kaydedildi:
Yayımlandı:PLoS One vol. 11, no. 1 (Jan 2016), p. e0147935
Yazar: Rechner, Steffen
Diğer Yazarlar: Berger, Annabell
Baskı/Yayın Bilgisi:
Public Library of Science
Konular:
American Mathematical Society
United States > US
Germany
Monte Carlo simulation
Computer programs
Applied mathematics
Graphs
Markov chains
Computer science
Upper bounds
Algorithms
Open source software
Economic
Methods
Sampling
Libraries
Probability distribution
Computer simulation
Markov analysis
Software
Online Erişim:Citation/Abstract
Full Text
Full Text - PDF
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!
Özet:We present the software library marathon, which is designed to support the analysis of sampling algorithms that are based on the Markov-Chain Monte Carlo principle. The main application of this library is the computation of properties of so-called state graphs, which represent the structure of Markov chains. We demonstrate applications and the usefulness of marathon by investigating the quality of several bounding methods on four well-known Markov chains for sampling perfect matchings and bipartite graphs. In a set of experiments, we compute the total mixing time and several of its bounds for a large number of input instances. We find that the upper bound gained by the famous canonical path method is often several magnitudes larger than the total mixing time and deteriorates with growing input size. In contrast, the spectral bound is found to be a precise approximation of the total mixing time.
ISSN:1932-6203
DOI:10.1371/journal.pone.0147935
Kaynak:Health & Medical Collection