Online jump and kink detection in segmented linear regression: Statistical optimality meets computational efficiency

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hüselitz, Annika, Li, Housen, Munk, Axel
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911653443928064
author Hüselitz, Annika
Li, Housen
Munk, Axel
author_facet Hüselitz, Annika
Li, Housen
Munk, Axel
contents We consider the problem of sequential (online) estimation of a single change point in a piecewise linear regression model under a Gaussian setup. We demonstrate that certain CUSUM-type statistics attain the minimax optimal rates for localizing the change point. Our minimax analysis unveils an interesting phase transition from a jump (discontinuity in function values) to a kink (a change in slope). Specifically, for a jump, the minimax rate is of order $\log (n) / n$ , whereas for a kink it scales as $(\log (n) / n)^{1/3}$, given that the sampling rate is of order $1/n$. We further introduce an online algorithm based on these detectors, which optimally identifies both a jump and a kink, and is able to distinguish between them. Notably, the algorithm operates with constant computational complexity and requires only constant memory per incoming sample. Finally, we evaluate the empirical performance of our method on both simulated and real-world data sets. An implementation is available in the R package FLOC on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Online jump and kink detection in segmented linear regression: Statistical optimality meets computational efficiency
Hüselitz, Annika
Li, Housen
Munk, Axel
Statistics Theory
62L12, 62C20, 62J20
We consider the problem of sequential (online) estimation of a single change point in a piecewise linear regression model under a Gaussian setup. We demonstrate that certain CUSUM-type statistics attain the minimax optimal rates for localizing the change point. Our minimax analysis unveils an interesting phase transition from a jump (discontinuity in function values) to a kink (a change in slope). Specifically, for a jump, the minimax rate is of order $\log (n) / n$ , whereas for a kink it scales as $(\log (n) / n)^{1/3}$, given that the sampling rate is of order $1/n$. We further introduce an online algorithm based on these detectors, which optimally identifies both a jump and a kink, and is able to distinguish between them. Notably, the algorithm operates with constant computational complexity and requires only constant memory per incoming sample. Finally, we evaluate the empirical performance of our method on both simulated and real-world data sets. An implementation is available in the R package FLOC on GitHub.
title Online jump and kink detection in segmented linear regression: Statistical optimality meets computational efficiency
topic Statistics Theory
62L12, 62C20, 62J20
url https://arxiv.org/abs/2503.05270