Robust Quickest Change Detection for Unnormalized ModelsDownload PDF

Published: 08 May 2023, Last Modified: 26 Jun 2023UAI 2023Readers: Everyone
Keywords: robust change detection, quickest change detection, SCUSUM, score matching, unnormalized models
TL;DR: We propose a new robust score-based quickest change detection algorithm that can be applied to unnormalized models.
Abstract: Detecting an abrupt and persistent change in the underlying distribution of online data streams is an important problem in many applications. This paper proposes a new robust score-based algorithm called RSCUSUM, which can be applied to unnormalized models and addresses the issue of unknown post-change distributions. RSCUSUM replaces the Kullback-Leibler divergence with the Fisher divergence between pre- and post-change distributions for computational efficiency in unnormalized statistical models and introduces a notion of the ``least favorable'' distribution for robust change detection. The algorithm and its theoretical analysis are demonstrated through simulation studies.
Supplementary Material: pdf
Other Supplementary Material: zip
0 Replies