skip to main content

DOE PAGESDOE PAGES

Title: Adaptive Sequential Monte Carlo for Multiple Changepoint Analysis

Process monitoring and control requires detection of structural changes in a data stream in real time. This paper introduces an efficient sequential Monte Carlo algorithm designed for learning unknown changepoints in continuous time. The method is intuitively simple: new changepoints for the latest window of data are proposed by conditioning only on data observed since the most recent estimated changepoint, as these observations carry most of the information about the current state of the process. The proposed method shows improved performance over the current state of the art. Another advantage of the proposed algorithm is that it can be made adaptive, varying the number of particles according to the apparent local complexity of the target changepoint probability distribution. This saves valuable computing time when changes in the changepoint distribution are negligible, and enables re-balancing of the importance weights of existing particles when a significant change in the target distribution is encountered. The plain and adaptive versions of the method are illustrated using the canonical continuous time changepoint problem of inferring the intensity of an inhomogeneous Poisson process, although the method is generally applicable to any changepoint problem. Performance is demonstrated using both conjugate and non-conjugate Bayesian models for the intensity.more » Lastly, appendices to the article are available online, illustrating the method on other models and applications.« less
Authors:
 [1] ;  [2]
  1. Imperial College, London (United Kingdom). Dept. of Mathematics; Heilbronn Inst. for Mathematical Research, Bristol (United Kingdom)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Report Number(s):
LA-UR-16-22735
Journal ID: ISSN 1061-8600
Grant/Contract Number:
AC52-06NA25396
Type:
Accepted Manuscript
Journal Name:
Journal of Computational and Graphical Statistics
Additional Journal Information:
Journal Volume: 26; Journal Issue: 2; Journal ID: ISSN 1061-8600
Publisher:
Taylor & Francis
Research Org:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org:
USDOE; Engineering and Physical Sciences Research Council (EPSRC)
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Mathematics
OSTI Identifier:
1340927

Heard, Nicholas A., and Turcotte, Melissa J. M.. Adaptive Sequential Monte Carlo for Multiple Changepoint Analysis. United States: N. p., Web. doi:10.1080/10618600.2016.1190281.
Heard, Nicholas A., & Turcotte, Melissa J. M.. Adaptive Sequential Monte Carlo for Multiple Changepoint Analysis. United States. doi:10.1080/10618600.2016.1190281.
Heard, Nicholas A., and Turcotte, Melissa J. M.. 2016. "Adaptive Sequential Monte Carlo for Multiple Changepoint Analysis". United States. doi:10.1080/10618600.2016.1190281. https://www.osti.gov/servlets/purl/1340927.
@article{osti_1340927,
title = {Adaptive Sequential Monte Carlo for Multiple Changepoint Analysis},
author = {Heard, Nicholas A. and Turcotte, Melissa J. M.},
abstractNote = {Process monitoring and control requires detection of structural changes in a data stream in real time. This paper introduces an efficient sequential Monte Carlo algorithm designed for learning unknown changepoints in continuous time. The method is intuitively simple: new changepoints for the latest window of data are proposed by conditioning only on data observed since the most recent estimated changepoint, as these observations carry most of the information about the current state of the process. The proposed method shows improved performance over the current state of the art. Another advantage of the proposed algorithm is that it can be made adaptive, varying the number of particles according to the apparent local complexity of the target changepoint probability distribution. This saves valuable computing time when changes in the changepoint distribution are negligible, and enables re-balancing of the importance weights of existing particles when a significant change in the target distribution is encountered. The plain and adaptive versions of the method are illustrated using the canonical continuous time changepoint problem of inferring the intensity of an inhomogeneous Poisson process, although the method is generally applicable to any changepoint problem. Performance is demonstrated using both conjugate and non-conjugate Bayesian models for the intensity. Lastly, appendices to the article are available online, illustrating the method on other models and applications.},
doi = {10.1080/10618600.2016.1190281},
journal = {Journal of Computational and Graphical Statistics},
number = 2,
volume = 26,
place = {United States},
year = {2016},
month = {5}
}

Works referenced in this record:

Bayesian anomaly detection methods for social networks
journal, August 2010
  • Heard, Nicholas A.; Weston, David J.; Platanioti, Kiriaki
  • The Annals of Applied Statistics, Vol. 4, Issue 2, p. 645-662
  • DOI: 10.1214/10-AOAS329