Back to Search
Start Over
Statistically and Computationally Efficient Change Point Localization in Regression Settings.
- Source :
-
Journal of Machine Learning Research . 2021, Vol. 22, p1-46. 46p. - Publication Year :
- 2021
-
Abstract
- Detecting when the underlying distribution changes for the observed time series is a fundamental problem arising in a broad spectrum of applications. In this paper, we study multiple change-point localization in the high-dimensional regression setting, which is particularly challenging as no direct observations of the parameter of interest is available. Specically, we assume we observe fxt; ytgn t=1 where fxtgn t=1 are p-dimensional covariates, fytgn t=1 are the univariate responses satisfying E(yt) = x> t for 1 tn and ft gn t=1 are the unobserved regression coefficients that change over time in a piecewise constant manner. We propose a novel projection-based algorithm, Variance Projected Wild Binary Segmentation (VPWBS), which transforms the original (difficult) problem of change-point detection in p-dimensional regression to a simpler problem of change-point detection in mean of a one-dimensional time series. VPWBS is shown to achieve sharp localization rate Op(1=n) up to a log factor, a signicant improvement from the best rate Op(1= p n) known in the existing literature for multiple change-point localization in high-dimensional regression. Extensive numerical experiments are conducted to demonstrate the robust and favorable performance of VPWBS over two state-of-the-art algorithms, especially when the size of change in the regression coefficients ft gn t=1 is small. [ABSTRACT FROM AUTHOR]
- Subjects :
- *CHANGE-point problems
*TIME series analysis
Subjects
Details
- Language :
- English
- ISSN :
- 15324435
- Volume :
- 22
- Database :
- Academic Search Index
- Journal :
- Journal of Machine Learning Research
- Publication Type :
- Academic Journal
- Accession number :
- 155404530