Scalable sum-shrinkage schemes for distributed monitoring large-scale data streams

DOI10.5705/SS.202015.0316MaRDI QIDQ4626674zbMATH OpenOpenAlexFDO

Authors Kun Liu, Ruizhi Zhang, Yajun Mei

Publication date 28 February 2019

Published in STATISTICA SINICA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1603.08652

zbMATH Keywords

change-pointCUSUMparallel computingquickest detectionsensor networkssum-shrinkage schemes

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: In this article, motivated by biosurveillance and censoring sensor networks, we investigate the problem of distributed monitoring large-scale data streams where an undesired event may occur at some unknown time and affect only a few unknown data streams. We propose to develop scalable global monitoring schemes by parallel running local detection procedures and by combining these local procedures together to make a global decision based on SUM-shrinkage techniques. Our approach is illustrated in two concrete examples: one is the nonhomogeneous case when the pre-change and post-change local distributions are given, and the other is the homogeneous case of monitoring a large number of independent $N(0,1)$ data streams where the means of some data streams might shift to unknown positive or negative values. Numerical simulation studies demonstrate the usefulness of the proposed schemes.

Recommendations

• Efficient scalable schemes for monitoring a large number of data streams
• Robust change detection for large-scale data streams
• Monitoring threshold functions over distributed data streams with node dependent constraints
• Optimal sequential detection in multi-stream data
• A new nonparametric monitoring of data streams for changes in location and scale via Cucconi statistic

Cited in

(16)

• Efficient scalable schemes for monitoring a large number of data streams
• Change detection via affine and quadratic detectors
• Asymptotic statistical properties of communication-efficient quickest detection schemes in sensor networks
• Robust change detection for large-scale data streams
• Adaptive Change Point Monitoring for High-Dimensional Data
• Univariate fast initial response statistical process control with taut strings
• Large-Scale Datastreams Surveillance via Pattern-Oriented-Sampling
• Rapid online plant leaf area change detection with high-throughput plant image data
• Hot-spots detection in count data by Poisson assisted smooth sparse tensor decomposition
• A Normality Test for High-dimensional Data Based on the Nearest Neighbor Approach
• Asymptotic optimality theory for active quickest detection with unknown postchange parameters
• A communication-efficient, online changepoint detection method for monitoring distributed sensor networks
• Bandit Change-Point Detection for Real-Time Monitoring High-Dimensional Data Under Sampling Control
• A speed-based estimator of signal-to-noise ratios
• MixFOCuS: a communication-efficient online changepoint detection method in distributed system for mixed-type data
• Scalable real-time monitoring system for ubiquitous smart space

This page was built for publication: Scalable sum-shrinkage schemes for distributed monitoring large-scale data streams

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4626674)