About the Project
Consider a large number of detectors each generating a data stream. The task is to detect online, distribution changes in a small fraction of the data streams.
We propose optimal algorithms that minimize the detection delay subject to a given average run length constraint.
We also compare these algorithms against previous approaches that include the use of mixture likelihood ratios and sum of CUSUMs.
Project Image
Team
Related Publications
Hock Peng Chan
Consider a large number of detectors each generating a datastream. The task is to detect online, distribution changes in a smallfraction of the data streams. Previous approaches to this probleminclude the use of mixture likelihood ratios and sum of CUSUMs. Weprovide here extensions and modifications of these approaches thatare…
Suported by the National University of Singapore grant R-155-000-158-112
Hock Peng Chan
Consider a large number of detectors each generating a datastream. The task is to detect online, distribution changes in a smallfraction of the data streams. Previous approaches to this probleminclude the use of mixture likelihood ratios and sum of CUSUMs. Weprovide here extensions and modifications of these approaches thatare…
The Annals of Statistics
Suported by the National University of Singapore grant R-155-000-158-112
