Projet ANR DETECT -- Multiple change-point detection

Multiple change-point detection

Last updated: October, 15th 2012 - Back to the the project page - Back to index

(2012) Toby Dylan Hocking, New sparse methods for clustering and segmentation, with applications to bioinformatics. Ph.D. dissertation, co-advised by Francis Bach and Jean-Philippe Vert.
(2012) Sylvain Arlot, Alain Celisse, Zaïd Harchaoui. Kernel change-point detection. Preprint.
[Hal] [arXiv]
(2010) Sylvain Arlot, Alain Celisse. Segmentation of the mean of heteroscedastic data via cross-validation. Statistics and Computing, 1--20. DOI: 10.1007/s11222-010-9196-x.
[journal] [pdf.gz] [supplementary material, pdf.gz] [Hal] [matlab code]

July, 2nd, 2012: closing meeting of the project, with the following talks:
- Tristan Mary-Huard: k-nearest neighbours (joint work with Alain Celisse)
- Zaïd Harchaoui (INRIA Grenoble): kernel change-point detection (joint work with Sylvain Arlot and Alain Celisse)
- Rémi Lajugie: metric learning for change-point detection (joint work with Sylvain Arlot and Francis Bach)
DETECT is supporting the ICML 2012 Workshop on RKHS and kernel-based methods.
June, 14th, 2012: Hypothesis Testing and Bayesian Inference: New Applications of Kernel Methods by Arthur Gretton (Gatsby Neuroscience Unit and University College London)
December, 16th, 2010: change-point detection and computer vision
May, 21st, 2010: Two talks about Efficient algorithms for multiple change-point detection by Guillem Rigaill (AgroParisTech and Institut Curie) and by Kevin Bleakley and Jean-Philippe Vert (Institut Curie).
[abstracts] [Guillem Rigaill's slides]
March, 11th, 2010: Change-point detection with kernels by Zaïd Harchaoui (INRIA Grenoble)