Seminar talks

Seminar talks

1. Relationship between sample size and architecture for the estimation of Sobolev functions using deep neural networks, Séminaire Operations Research, Departement of Mathematical Engineering, UC Louvain, Belgium, February 12, 2024.  

2. Benign overfitting : analysis of the generalisation paradox, INRIA Lille Modal seminar, June 7, 2022.

3. A finite sample analysis of the double descent phenomenon for ridge function estimation, Seminaire du Laboratoire de Probabilités, Statistique et Modélisation (LPSM, UMR 8001), 15 december 2020. 

4. A finite sample analysis of the double descent phenomenon, INRIA Lille Modal seminar, November 17, 2020. 

5. Presentation de l'article "Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin, de Colin Wei, Tengyu Ma" au GT Fondements théoriques du deep learning, Scidolyse, Institut Camille Jordan, 13 February 2020, Lyon. 

6. Some optimisation problems in the Data Science Division at the National Physical Laboratory, Data Science Seminar, Mathematical Institute, Oxford, February 15, 2019. 

7. De-mélange multi-noyaux et super-résolution à l'aide d'une extension de la méthode des Matrix Pencils de Moitra, Rencontres de Statistiques Lyonnaises, February, 12, 2019. 

8. Méthodes de gradient incrémentales et application a l'estimation MoM, Seminaire du laboratoire ERIC, February 11, 2019.

9. Column selection and feature extraction, Math. Department, University of Kontanz, November 20, 2018. 

10. Talk at the optimisation club, Alan Turing Institute, London, November 7, 2018.

11.  Column/Feature extraction: old and new results, Theory  and Algorithms in Data Science, Alan Turing Institute, London, July 17, 2018.

12. Convex regularised least squares estimation for low rank tensors and application of optical coherence tomography, UCL Center for Inverse Problems, February 2, 2018.  

13. The LASSO when the design is not coherent, Quantitative Methods Seminar, St Gallen, Switzerland, March 13 2017. 

14. An elementary approach to Robust PCA, Seminaire de Statistiques, Universite de Bourgogne Franche-Comte, September 2016, Dijon, France.

15. Optimal sensor placement in Smart Grids: an approach based on semi-definite relaxation and sensitivity analysis, Universite de Franche-Comte, Probability and Statistics Seminar, 11 September 2016, Besancon, France. 

16. Some low rank estimation problems in Times Series and Clustering, UCL, London, July 7, 2016. 

17. Estimation of Gaussian Mixture Models via mixted nuclear/$\ell_\infty$/$\ell_1$-norm penalization, Statistics and Probability seminar, Lille 1, may 24, 2016.

18. Survey on sparse recovery, Seminar, University of Surrey, Guildford, May 5 2016. 

19. Low rank tensor recovery via convex optimization, Statistics seminar, LJK Grenoble, april 23 2015. Slides. 

20. Clustering par optimisation convexe, Statistics seminar, ENS Rennes, april 10 2015. Slides.

21. A new criterion for design matrices in the LASSO, Probabilty seminar, Université du Luxembourg, february 26 2015. Slides

22. Le LASSO pour des matrices de design non necessairement incoherentes, Séminaire Signal-Apprentissage. Université Aix-Marseille, march 15 2012. Slides and Video

23. Le Lasso avec variance inconnue. Séminaire de Statistique INRIA Lille-Nord Europe, mai 31 2011, Villeneuve d'Asq. Slides

24. Le Lasso avec variance inconnue. Séminaire de Statistique Université Montpellier 2, mai 9 2011, Montpellier. Slides

25. Le Lasso avec variance inconnue. Séminaire de Statistique Université Paul Sabatier, march 29 2011, Toulouse. 

26. Lasso et extensions, ou le compressed sensing en milieu bruité, Groupe de Travail Compressed Sensing, Institut Henri Poincaré, March 11 2009. Paris. 

27. Lagrangian relaxation of the compressed sensing problem, Statistics seminar, Boston University, November 4 2008. Boston MA   

28. Relaxation lagrangienne du probleme de Compressed Sensing. Rencontres Probabilites-Statistiques Besancon-Dijon, January 2008. Dijon.

29. Introduction au Compressed Sensing. Seminaire de Probabilite et Statistiques, November 2007. Besancon.

30. Une generalisation du modele de Diggle, Tawn et Moyeed en geostatistique, (with D. Pleydell) Seminaire de Probabilite et Statistiques, Universite de Lille 1, mai 2006. Abstract.

31. A Stochastic Bundle Method, Seminaire SMG, Han sur Lesse (Belgique), Avril 2000 Slides.

32. A Short Introduction to Bundle Methods, Seminaire du Service de Mathematiques de la Gestion, Universite Libre de Bruxelles, Fevrier 2000 Slides.

33. Semidefinite Programming and Combinatorial Optimization, Seminaire SMG, Borzee (Belgique), mai 1999 Slides.

34. Approches EM et Kullback-proximale pour la maximisation de vraisemblance et application aux melanges, Seminaire IS2, INRIA Rhone Alpes, Slides.

35. Approches EM et Kullback-proximale pour la maximisation de vraisemblance, Seminaire LMC Universite Joseph Fourier Grenoble, decembre 1998.