Adaptive Weighted Total Variation Penalty for Precise Change Point Detection
Australian & New Zealand Journal of Statistics · 2026-06 · 68 (2)
DOI: 10.1111/anzs.70053 ↗Kurz gefasst
Fachartikel in der Zeitschrift Australian & New Zealand Journal of Statistics, online erschienen am 20.05.2026. Verfasst von Dong‐Young Lee und 2 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
Total variation (TV)‐based methods, such as the fused lasso, are standard for change point detection but are impaired by issues like local monotonicity. To address these limitations, this study comparatively analyses the fused lasso with two alternative methodologies. These methodologies are the Penalised Regression Spline (PRS) and a novel Adaptive Penalised Regression Spline (APRS) that incorporates data‐adaptive weights. Using an efficient coordinate descent algorithm, we evaluated the three methods on both simulated and real‐world data. The comparative analysis, conducted under various Signal‐to‐Noise Ratio (SNR) conditions, revealed that APRS demonstrated superior performance, particularly in minimising false positives.
Förderung
- National Research Foundation of Korea
Zitieren
APA
Lee, D., Bak, K., & Jhong, J. (2026). Adaptive Weighted Total Variation Penalty for Precise Change Point Detection. Australian & New Zealand Journal of Statistics, 68(2). https://doi.org/10.1111/anzs.70053
Vancouver
Lee D, Bak K, Jhong J. Adaptive Weighted Total Variation Penalty for Precise Change Point Detection. Australian & New Zealand Journal of Statistics. 2026;68(2). doi:10.1111/anzs.70053
BibTeX
@article{Lee2026,
author = {Lee, Dong‐Young and Bak, Kwan‐Young and Jhong, Jae‐Hwan},
title = {Adaptive Weighted Total Variation Penalty for Precise Change Point Detection},
journal = {Australian & New Zealand Journal of Statistics},
year = {2026},
volume = {68},
number = {2},
doi = {10.1111/anzs.70053}
}
EUVIMED