LJKProbability & Statistics Seminar

On Thursday January 30 2014 at 14h00 in Salle 1  Tour IRMA

Seminary of Farida ENIKEEVA (LJK / Mistis)

Highdimensional changepoint detection with sparse alternatives

Summary

We consider the problem of detecting a change in mean in a sequence of Gaussian vectors. We assume that the change occurs only in some of the components of the vector. We construct a procedure of testing the change in mean adaptive to the number of nonzero 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 the test and show its rateoptimality.
This is a joint work with Zaid Harchaoui.
