Training Neural Networks for Sequential Change-Point Detection

Junghwan Lee; Yao Xie; Xiuyuan Cheng

ICASSP 2023accepted0 citations

Training Neural Networks for Sequential Change-Point Detection

Abstract

Detecting an abrupt distributional shift of a data stream, known as change-point detection, is a fundamental problem in statistics and machine learning. We introduce a novel approach for online change-point detection using neural net-works. To be specific, our approach is training neural net-works to compute the cumulative sum of a detection statistic sequentially, which exhibits a significant change when a change-point occurs. We demonstrated the superiority and potential of the proposed method in detecting change-point using both synthetic and real-world data. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

BibTeX

@inproceedings{icassp2023_trainingneuralne,
  title = {Training Neural Networks for Sequential Change-Point Detection},
  author = {Junghwan Lee and Yao Xie and Xiuyuan Cheng},
  booktitle = {ICASSP 2023},
  year = {2023}
}