## BiographyStephane Chretien studied at Ecole Normale Superieure (Cachan) and obtained his PhD in Electrical Engineering from the Universite Paris Sud Orsay in 1996, where he worked on successive projection methods for nonconvex set theoretic feasibility problems in signal processing and control applications. He then joined the University of Michigan (Ann Arbor) as a post-doctorate in Alfred Hero's group where here developed a Kullback-Proximal framework for the analysis of estimation algorithms in statistics and machine learning with application to Positron Emission Tomography. He then went back to France as a researcher in the NUMOPT team lead by Claude Lemarechal at INRIA where he studied numerical methods for nonsmooth optimization and EM-types algorithms for clustering with the group of Gilles Celeux. In 1999, he joined Martine Labbe's Mathematics for Decision's team in Brussels, where he studied network flow problems and convex relaxations for urban traffic modelling and control. In 2000, he was appointed Assistant Professor in the Mathematics Laboratory (Probability and Statistics team) at the Universite de Franche Comte, Besancon where he studied efficient algorithms for Compressed Sensing, time series analysis and clustering and contributed theoretical results on sparse recovery and finite random matrices. He joined the National Physical Laboratory (Mathematics and Modelling) in September 2015. ## Research interests and projectsStephane's research interests are in computational statistics, big data, machine learning, compressed sensing optimisation. He has worked on various projects in time series analysis, machine learning, clustering, image segmentation, genetics, scheduling, combinatorial optimization and has been funded via both industrial and academic grants. He also offers consultancy in all potential technical challenges for the industry, involving high dimensional statistics, compressed sensing, large scale deterministic and stochastic optimisation. ## News !
Optimisation for machine learning - ASMDA 2017Mathematics of Measurement. Big data: Convergence of statistics and optimization - CMStatistics 2018## Recent publications- An elementary approach to the problem of column selection in a rectangular matrix (with S. Darses), LNCS, Proceeding of MOD 2017, to appear.
- On the pinning controllability of complex networks using perturbation theory of extreme singular values. Application to synchronisation in power grids, (with S. Darses, C. Guyeux and P. Clarkson), Numerical Algebra, Control and Optimization, to appear.
- On the subdifferential of symmetric convex functions of the spectrum for symmetric and orthogonally decomposable tensors
*Linear Algebra and its Applications,*(with T. Wei), to appear. - Sensing tensors with Gaussian filters,
*IEEE Trans. Information Theory*(with T. Wei), 63 (2), pp. 843-852 (2017). - Enhancing Prony's method by nuclear norm
penalization and extension to missing data,
*Signal, Image and Video Processing*(with B. Al-Sarray, P. Clarkson and G. Cottez), (2017). - Simulation-based estimation of branching models
for LTR retrotransposons,
*Bioinformatics*(with S. Moulin, N. Seux, C. Guyeux, E. Lerat, et al., 33 (3), pp. 320-326, (2016). - A Bregman-proximal point algorithm for robust non-negative matrix factorization with possible missing values and outliers-application to gene expression analysis (with C. Guyeux, B. Conesa, R. Delage-Mouroux, M. Jouvenot, F. Descotes),
*BMC Bioinformatics*17 (8), 284 (2016). - A lower bound on the expected optimal value of certain random linear programs and application to shortest paths in Directed Acyclic Graphs and reliability
- Dendrochemical assessment of mercury releases from a pond and dredged-sediment landfill impacted by a chlor-alkali plant (with F. Maillard, O. Girardclos, M. Assad, C. Zappelini, J. Maria Pérez Mena, L. Yung, C. Guyeux, G. Bigham, C. Cosio, M. Chalot),
*Environmental research*,*148*, pp. 122-126 (2016). - Gene expression signature functional annotation of breast cancer tumors in function of age, (with P. Jezequel et al.)
*BMC Medical Genomics*(2015) - Job scheduling using successive linear programming approximations of a sparse model, (with
J-M Nicod, L Philippe, V Rehn-Sonig and L Toch), Concurrency and Computation: Practice and Experience,**27**, 14, pp 3561-3586 (2015) - Von Neumann's trace inequality for tensors (with T Wei), Linear Algebra and its Applications,
**482**, 1, pp 149-157 (2015) - On the spacings between the successive zeros of the Laguerre polynomials (with S Darses), Proceedings of the AMS,
**143**, 10, pp 4383-4388 (2015) - Sparse recovery with unknown variance: a LASSO-type approach (with S Darses), IEEE Trans Information Theory,
**60**, 7, pp 3970-3988 (2014) - Multivariate GARCH estimation via a Bregman-proximal trust-region method (with Juan-Pablo Ortega), Computational Statistics and Data Analysis,
**76**, pp 210-236 (2014) - High-overtone Bulk Acoustic Resonator as passive Ground Penetrating RADAR cooperative targets,(with J-M Friedt, A Saintenoy, T Baron, E Lebrasseur, T Laroche, S Ballandras, M Griselin), Journal of Applied Physics,
**113**, 134904 (2013) - Invertibility of random submatrices via tail decoupling and a Matrix Chernoff Inequality, (with Sebastien Darses), Statistics and Probability Letters,
**82**, 7, pp 1479-1487 (2012) - EM type algorithms for likelihood optimization with non-differentiable penalties, (with Alfred O Hero and Herve Perdry), Ann Inst Stat Math,
**64**, 4, pp 791-809 (2012) - An alternating l1 relaxation for compressed sensing, IEEE Signal Processing Letters,
**17**, 2, pp 181-184 (2010). - Mixtures of GAMs for habitat suitability analysis with overdispersed presence/absence data. (with D. Pleydell)
*Computational statistics & data analysis*,*54*(5), 1405-1418 (2010). - Using the eigenvalue relaxation for binary least-squares estimation problems (with F. Corset).
*Signal Processing*,*89*(11), 2079-2091 (2009). - On EM algorithms and their proximal generalizations. (with A. O. Hero)
*ESAIM: Probability and Statistics*,*12*, 308-326 (2008).
- Degeneracy in the maximum likelihood estimation of univariate Gaussian mixtures with EM (with C. Biernacki).
*Statistics & probability letters*,*61*(4), 373-382 (2003). - A component-wise EM algorithm for mixtures (with Celeux, G., Forbes, F., Mkhadri, A.).
*Journal of Computational and Graphical Statistics (2002)*. - Kullback proximal algorithms for maximum-likelihood estimation (with A. Hero).
*IEEE transactions on information theory*,*46*(5), 1800-1810 (2000). - Cyclic projection methods on a class of nonconvex sets (with Pascal Bondon)..
*Numer. Funct. Anal. Optim*.*17, no. 1-2, 37--56**(1996)*.
See Google Scholar for a full publication list or here. The list of my recent talks is here. ## TeachingLecture notes, courses, ... are here. ## Contact detailsE-mail: stephane.chretien@npl.co.uk |

### Stephane Chretien

Selection | File type icon | File name | Description | Size | Revision | Time | User |
---|