Home > Research > Publications & Outputs > Nonparametric multiple change point estimation ...

Research

Associated organisational units

Links

Text available via DOI:

Keywords

View graph of relations

Nonparametric multiple change point estimation in highly dependent time series

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Nonparametric multiple change point estimation in highly dependent time series. / Khaleghi, Azadeh; Ryabko, Daniil.
In: Theoretical Computer Science, Vol. 620, 21.03.2016, p. 119-133.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Khaleghi, A & Ryabko, D 2016, 'Nonparametric multiple change point estimation in highly dependent time series', Theoretical Computer Science, vol. 620, pp. 119-133. https://doi.org/10.1016/j.tcs.2015.10.041

APA

Khaleghi, A., & Ryabko, D. (2016). Nonparametric multiple change point estimation in highly dependent time series. Theoretical Computer Science, 620, 119-133. https://doi.org/10.1016/j.tcs.2015.10.041

Vancouver

Khaleghi A, Ryabko D. Nonparametric multiple change point estimation in highly dependent time series. Theoretical Computer Science. 2016 Mar 21;620:119-133. Epub 2015 Nov 11. doi: 10.1016/j.tcs.2015.10.041

Author

Khaleghi, Azadeh ; Ryabko, Daniil. / Nonparametric multiple change point estimation in highly dependent time series. In: Theoretical Computer Science. 2016 ; Vol. 620. pp. 119-133.

Bibtex

@article{1dc6431aa0564a0eb018c457adcd83ab,
title = "Nonparametric multiple change point estimation in highly dependent time series",
abstract = "Given a heterogeneous time-series sample, the objective is to find points in time, called change points, where the probability distribution generating the data has changed. The data are assumed to have been generated by arbitrary unknown stationary ergodic distributions. No modelling, independence or mixing assumptions are made. A novel, computationally efficient, nonparametric method is proposed, and is shown to be asymptotically consistent in this general framework. The theoretical results are complemented with experimental evaluations.",
keywords = "Change point analysis, Stationary ergodic time series, Unsupervised learning, Consistency",
author = "Azadeh Khaleghi and Daniil Ryabko",
year = "2016",
month = mar,
day = "21",
doi = "10.1016/j.tcs.2015.10.041",
language = "English",
volume = "620",
pages = "119--133",
journal = "Theoretical Computer Science",
issn = "0304-3975",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Nonparametric multiple change point estimation in highly dependent time series

AU - Khaleghi, Azadeh

AU - Ryabko, Daniil

PY - 2016/3/21

Y1 - 2016/3/21

N2 - Given a heterogeneous time-series sample, the objective is to find points in time, called change points, where the probability distribution generating the data has changed. The data are assumed to have been generated by arbitrary unknown stationary ergodic distributions. No modelling, independence or mixing assumptions are made. A novel, computationally efficient, nonparametric method is proposed, and is shown to be asymptotically consistent in this general framework. The theoretical results are complemented with experimental evaluations.

AB - Given a heterogeneous time-series sample, the objective is to find points in time, called change points, where the probability distribution generating the data has changed. The data are assumed to have been generated by arbitrary unknown stationary ergodic distributions. No modelling, independence or mixing assumptions are made. A novel, computationally efficient, nonparametric method is proposed, and is shown to be asymptotically consistent in this general framework. The theoretical results are complemented with experimental evaluations.

KW - Change point analysis

KW - Stationary ergodic time series

KW - Unsupervised learning

KW - Consistency

U2 - 10.1016/j.tcs.2015.10.041

DO - 10.1016/j.tcs.2015.10.041

M3 - Journal article

VL - 620

SP - 119

EP - 133

JO - Theoretical Computer Science

JF - Theoretical Computer Science

SN - 0304-3975

ER -