Section: New Results

Multiple change-point detection

Participants : Alain Celisse, Guillemette Marot.

This is a joint work with Morgane Pierre-Jean and Guillem Rigaill (Univ. Evry).

The paper related to the work described in previous MODAL team reports (sections Kernel change point) has been pursuied and made available on Arxiv [42]. For recall, this work focuses on the problem of detecting abrupt changes arising in the full distribution of the observations (not only in the mean or variance). It provides greatly improved algorithms in terms of computational complexity (both in time and space). The computational and statistical performances of these new algorithms have been assessed through empirical experiments, which are detailed in the preprint.