Clustering piecewise stationary processes

Khaleghi, Azadeh and Ryabko, Daniil (2020) Clustering piecewise stationary processes. In: 2020 IEEE International Symposium on Information Theory. IEEE, pp. 2753-2758. ISBN 9781728164335

[img]
Text (nstclust)
nstclust.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (283kB)

Abstract

The problem of time-series clustering is considered in the case where each data-point is a sample generated by a piecewise stationary process. While stationary processes comprise one of the most general classes of processes in nonparametric statistics, and in particular, allow for arbitrary long-range dependencies, their key assumption of stationarity remains restrictive for some applications. We address this shortcoming by considering piecewise stationary processes, studied here for the first time in the context of clustering. It turns out that this problem allows for a rather natural definition of consistency of clustering algorithms. Efficient algorithms are proposed which are shown to be asymptotically consistent without any additional assumptions beyond piecewise stationarity. The theoretical results are complemented with experimental evaluations.

Item Type:
Contribution in Book/Report/Proceedings
Additional Information:
©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
ID Code:
143198
Deposited By:
Deposited On:
27 May 2020 08:25
Refereed?:
Yes
Published?:
Published
Last Modified:
07 Mar 2021 01:27