arXiv (Cornell University) · 2013 · 21 citations · 1 references
ComputingComputer ScienceComputer VisionMachine LearningTime Series AnalysisChange DetectionChange-point DetectionDigital Signal ProcessingGaussian ProcessesSignal Detection TheorySignal ProcessingAbrupt Change DetectionAdaptive Change-point DetectionAlternative HypothesisChange-point LocalizationHigh-dimensional Change-point DetectionSparse Change-point DetectionTrend Change Point Detection
We consider the problem of detecting a change in mean in a sequence of Gaussian vectors. Under the alternative hypothesis, the change occurs only in some subset of the components of the vector. We propose a test of the presence of a change-point that is adaptive to the number of changing components. Under the assumption that the vector dimension tends to infinity and the length of the sequence grows slower than the dimension of the signal, we obtain the detection boundary for this problem and prove its rate-optimality.
1