A0465
Title: Practical and powerful kernel-based change-point detection
Authors: Hoseung Song - KAIST (Korea, South) [presenting]
Abstract: Change-point analysis plays a significant role in various fields to reveal discrepancies in distribution in a sequence of observations. While a number of algorithms have been proposed for high-dimensional data, kernel-based methods have not been well explored due to difficulties in controlling false discoveries and mediocre performance. A new kernel-based framework is proposed that makes use of an important pattern of data in high dimensions to boost power. Analytic approximations of the significance of the new statistics are derived, and fast tests based on the asymptotic results are proposed, offering easy off-the-shelf tools for large datasets. The new tests show superior performance for a wide range of alternatives when compared with other state-of-the-art methods. These new approaches are illustrated through an analysis of phone-call network data. All proposed methods are implemented in an R package kerSeg.
