Dynamic Search on a Tree with Information-Directed Random Walk

Chao Wang, Qing Zhao, Kobi Cohen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The problem of detecting a few anomalous processes among a large number of data streams is considered. At each time, aggregated observations can be taken from a chosen subset of the processes, where the chosen subset conforms to a given tree structure. The random observations are drawn from a general distribution that may depend on the size of the chosen subset and the number of anomalous processes in the subset. We propose a sequential search strategy by devising an information-directed random walk (IRW) on the tree-structured observation hierarchy. The sample complexity of the IRW policy is shown to be asymptotically optimal with respect to the detection accuracy and order optimal with respect to the number of data streams. The results also find applications in noisy group testing, active learning, and channel coding with feedback.

Original languageEnglish
Title of host publication2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781538635124
DOIs
StatePublished - 24 Aug 2018
Event19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018 - Kalamata, Greece
Duration: 25 Jun 201828 Jun 2018

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
Volume2018-June

Conference

Conference19th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018
Country/TerritoryGreece
CityKalamata
Period25/06/1828/06/18

Keywords

  • Sequential design of experiments
  • active hypothesis testing
  • anomaly detection
  • channel coding with feedback
  • noisy group testing

Fingerprint

Dive into the research topics of 'Dynamic Search on a Tree with Information-Directed Random Walk'. Together they form a unique fingerprint.

Cite this