Robust inference for change points in high dimension

This paper proposes a new test for change point in the mean of high-dimensional data based on spatial sign and self-normalization. The is easy to implement with no tuning parameters, robust heavy-tailedness theoretically justified both fixed-n sequential asymptotics under null alternatives, where n sample size. We demonstrate that provide better approximation finite distribution thus should be preferred testing testing-based estimation. To estimate number locations when multiple change-points are present, we propose combine p-value seeded binary segmentation (SBS) algorithm. Through numerical experiments, show procedures respect strong coordinate-wise dependence, whereas their non-robust counterparts proposed Wang et al. (2022)[28] appear under-perform. A real example also provided illustrate robustness broad applicability its corresponding estimation