Graph-Based Change-Point Detection for Partially Observed High-Dimensional Data
Abstract
Partial missingness is common in high-dimensional data, but most existing change-point procedures are developed for fully observed sequences. We introduce gMiss, a graph-based framework for testing and localizing a change in the observed-data distribution of a partially observed high-dimensional sequence. The method treats the observed values together with the missingness indicators as the object of inference, so the target alternative is a change in the induced observed data law. It is designed for general distributional changes and requires neither sparsity nor Gaussianity. When the augmented observations are independent, the full permutation test controls type I error in finite samples. The procedure combines graph scans based on elementwise imputation and distance imputation. The two scans capture complementary graph patterns. Simulation results indicate that gMiss maintains accurate null calibration across the MCAR and MAR designs considered, remains competitive under Gaussian location alternatives, and exhibits strong power and localization performance in many non-Gaussian location and scale settings. We further illustrate the practical utility of the method through an application to genomic copy-number data, where gMiss identifies additional candidate boundaries that are visually plausible in the raw heatmap.
Related
- Nonparametric Change-Point Detection and Inference for High-Dimensional Distributions
- Adaptable High-Dimensional Change Point Detection via Ridge Regularization
- Partially Observed McKean--Vlasov Control with Vanishing Observation Intensities
- Multiple Change Point Detection in the Mean and Covariance of High-Dimensional Matrix Time Series
- A Stochastic Maximum Principle for Partially Observed Jump-Diffusion Systems with State-Dependent Counting-Process Observations
BibTeX
@misc{liu2026graphbased,
title = {{Graph-Based Change-Point Detection for Partially Observed High-Dimensional Data}},
author = {Mingshuo Liu and Hao Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.06550},
eprint = {2609.06550},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06550},
}
RIS
TY - UNPB
TI - Graph-Based Change-Point Detection for Partially Observed High-Dimensional Data
AU - Mingshuo Liu
AU - Hao Chen
PY - 2026
DA - 2026/09/06
PB - arXiv
DO - 10.48550/arxiv.2609.06550
UR - https://arxiv.org/abs/2609.06550
AB - Partial missingness is common in high-dimensional data, but most existing change-point procedures are developed for fully observed sequences. We introduce gMiss, a graph-based framework for testing and localizing a change in the observed-data distribution of a partially observed high-dimensional sequence. The method treats the observed values together with the missingness indicators as the object of inference, so the target alternative is a change in the induced observed data law. It is designed for general distributional changes and requires neither sparsity nor Gaussianity. When the augmented observations are independent, the full permutation test controls type I error in finite samples. The procedure combines graph scans based on elementwise imputation and distance imputation. The two scans capture complementary graph patterns. Simulation results indicate that gMiss maintains accurate null calibration across the MCAR and MAR designs considered, remains competitive under Gaussian location alternatives, and exhibits strong power and localization performance in many non-Gaussian location and scale settings. We further illustrate the practical utility of the method through an application to genomic copy-number data, where gMiss identifies additional candidate boundaries that are visually plausible in the raw heatmap.
ER -