Differentially Private Change-Point Detection
Abstract
The change-point detection problem seeks to identify distributional changes at an unknown change-point k* in a stream of data. This problem appears in many important practical settings involving personal data, including biosurveillance, fault detection, finance, signal detection, and security systems. The field of differential privacy offers data analysis tools that provide powerful worst-case privacy guarantees. We study the statistical problem of change-point problem through the lens of differential privacy. We give private algorithms for both online and offline change-point detection, analyze these algorithms theoretically, and then provide empirical validation of these results.
Cite
Text
Cummings et al. "Differentially Private Change-Point Detection." Neural Information Processing Systems, 2018.Markdown
[Cummings et al. "Differentially Private Change-Point Detection." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/cummings2018neurips-differentially/)BibTeX
@inproceedings{cummings2018neurips-differentially,
title = {{Differentially Private Change-Point Detection}},
author = {Cummings, Rachel and Krehbiel, Sara and Mei, Yajun and Tuo, Rui and Zhang, Wanrong},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {10825-10834},
url = {https://mlanthology.org/neurips/2018/cummings2018neurips-differentially/}
}