Guillaume Lecué

guillaume.lecue@univ-mlv.fr

Contact

Current situation

I am a CNRS researcher at the Laboratoire d'Analyse et Mathématiques appliquées UMR 8050.

Research interests

Learning theory; Empirical processes theory; Compressed sensing.

New and past events

  • Workshop in Marne-la-vallée, every tuesday, 10:45, room 3B82: Analysis, Probability and statistics.
  • Conference in Marne-la-vallée, Monday, 17th of May to Friday, 21th of May: Probability and Geometry in high dimensions.
  • Fall school, November 16-20, 2009: Interaction between compressed sensing, random matrices and high dimensional geometry.
  • Publications and preprints

    1. G. Lecué, "Empirical risk minimization is optimal for the convex aggregation problem."
      To appear in Bernoulli journal, 2012.
    2. S. Gaïffas and G. Lecué, "Weighted algorithms for compressed sensing and Matrix completion." Submitted, 2011.
    3. G. Lecué and S. Mendelson, "General non-exact oracle inequalities in the unbounded case." To appear in The annals of Statistics, 2012. "Supplementary material to "General non-exact oracle inequalities in the unbounded case"."
    4. D. Chafaï, O. Guédon, G. Lecué and A. Pajor, "Interactions between compressed sensing, Random matrices and high-dimensional geometry." Under revision in the collection "Panoramas et synthèse" of the SMF.
    5. G. Lecué and S. Mendelson, "On the optimality of the empirical risk minimization procedure for the convex aggregation problem." To appear in Annales de l'institut Henri Poincaré.
    6. G. Lecué and C. Mitchell, "Oracle inequalities for cross-validation type procedures." Submitted, 2010.
    7. G. Lecué and S. Mendelson, "On the optimality of the aggregate with exponential weights for low temperatures." To appear in Bernoulli Journal.
    8. S. Gaïffas and G. Lecué, "Sharp oracle inequalities for high-dimensional matrix prediction." IEEE Transactions on Information Theory, 57 (10), p. 6942-6957.
    9. S. Gaïffas and G. Lecué, "Hyper-sparse optimal aggregation." Journal of Machine Learning research, 12(Jun):1813-1833, 2011.
    10. G. Lecué and S. Mendelson, "Sharper lower bounds on the performance of the Empirical Risk Minimization Algorithm." Bernoulli, 16(3), 2010, 605-613.
    11. K. Bertin and G. Lecué, "Selection of variables and dimension reduction in high-dimensional non-parametric regression." Electronic Journal of Statistics, Vol. 2, pp. 1224-1241. 2008.
    12. G. Lecué and S. Mendelson, "Aggregation via Empirical Risk Minimization." Probability theory and related fields, Vol. 145, Number 3-4, pp. 591-613. Novembre, 2009
    13. C. Chesneau and G. Lecué, "Adapting to Unknown Smoothness by Aggregation of Thresholded Wavelet Estimators." Statistica Sinica, Vol. 19, Number 4, October 2009, pp. 1407-1418
    14. G. Lecué, "Classification with minimax fast rates for Classes of Bayes Rules with Sparse Representation." Electronic Journal of Statistics, Vol. 2, pp. 741-773. 2008
    15. S. Gaïffas and G. Lecué, "Optimal rates and adaptation in the Single-Index Model using aggregation." Electronic Journal of Statistics, Vol. 1, pp. 538-573. 2007
    16. G. Lecué, "Suboptimality of Penalized Empirical Risk Minimization In Classification."
      20th Annual Conference On Learning Theory, COLT07. Proceedings. Bshouty, Gentile (Eds.). Springer. LNAI 4539, 142-156. Springer.
    17. G. Lecué, "Optimal rates of aggregation in classification under low noise assumption."
      Bernoulli 13(4), 2007, 1000-1022.
    18. G. Lecué, "Simultaneous adaptation to the margin and to complexity in classification."
      Annals of Statistics, Vol. 35, No. 4. pp. 1698-1721. August 2007.
    19. G. Lecué, "Optimal oracle inequality for aggregation of classifiers under low noise condition."
      19th Annual Conference On Learning Theory, COLT06. Proceedings. Gabor Lugosi, Hans Ulrich Simon (Eds.). Springer. LNAI 2006, 364-378. "Mark Fulk award" for the best student paper.
    20. G. Lecué, "Lower Bounds and Aggregation in Density Estimation."
      Journal of Machine Learning Research, 7(Jun):971-981, 2006.
    21. My PhD manuscript is available here and the slides of my PhD defense are available here.
      My Habilitation manuscript is available here and the slides of my HDR defense are available here.

    Invitations, presentations

    Marseille(dec.05): Statistical workshop at CIRM. Invited by Laurent Cavalier. Marseille - Luminy. France.
    Atlanta(jan.06): Statistic seminary of Georgia Institute of Technology (Georgia Tech). Invited by Vladimir Koltchinskii. Atlanta. USA.
    Berkeley(feb.06): Statistic seminary of the department of computer science at the university of California Berkeley. Invited by Peter Bartlett. Berkeley. USA.
    Berkeley(fev.06): Statistic seminary of the department of statistics at the university of California Berkeley. Invited by Bin Yu. Berkeley. USA.
    Aussois(march06): Statistical workshop for young probabilists and statisticians.Invited by Marc Hoffmann. Aussois. France.
    ENS Ulm(june06): Statistical workshop at ENS. Invited by Gilles Stoltz. Paris. France. You can watch the talk here (in French)
    Pittsburgh(june06): 19th Annual Conference on Learning Theory, COLT06. Pittsburgh. USA.
    Paris 6 (oct.06): Statistic seminary of the Laboratoire de Probabilité et Modèles Aléatoires. Invited Stéphane Boucheron and Alexandre Tsybakov. Paris. France.
    Marseille(dec.06): Statistical workshop at CIRM. Invited by Laurent Cavalier. Marseille. France.
    Grenoble(Jan.07): Statistic seminary of the Laboratoire Jean Kuntzman. Invited by Anatolie Iouditski. Grenoble. France.
    Marseille(March07): Statistical workshop at CIRM. Invited by Oleg Lepski and Laurent Cavalier. Marseille. France.
    ENS Ulm(March07): Statistical workshop at ENS. Invited by Gilles Stoltz. Paris. France. You can watch the talk here (in French)
    Praz-sur-Arly(June07): SMAI 2007. Invited by Stéphane Boucheron. France.
    San Diego(June07): 20th Annual Conference on Learning Theory, COLT07. San Diego. USA.
    Lisboa(August07): International Statistical Institute, ISI07. Invited by Feng Liang. Lisboa. Portugal.
    Toulouse(February08): Statistics seminary of Laboratoire de Statistique et Probabilités (LSP) Université Paul-Sabatier (Toulouse III) . Invited by Béatrice Laurent. Toulouse. France.
    Valparaiso(March08): Statistics seminary of Departamento de Estadística Universidad de Valparaíso. Invited by Karine Bertin. Valparaiso. Chile.
    Zürich(Oct08): Statistics seminary of Seminar für Statistik of ETH. Invited by Sara van de Geer. Zürich. Swiss.
    Göttingen(Nov08): Workshop "Statistical regularization and qualitative constraints". Invited by Sara van de Geer. Göttingen. Germany.
    ENS Ulm(Dec08): Statistical workshop at ENS. Invited by Gilles Stoltz. Paris. France.
    LPMA(Jan09): Statistical workshop at LPMA. Invited by Alexandre Tsybakov and Stéphane Boucheron. Paris. France.
    Canberra(Sept09): Statistical workshop at MSI. Invited by Alan Welsh. Canberra. Australia.
    Hamburg(March10): Statistical seminar. Invited by Angelika Rohde. Hamburg. Germany.
    Cambridge(Nov11): Statistical seminar. Invited by Richard Samworth. Cambridge. UK
    Some of my slides are available here:

    Awards

  • "Mark Fulk award" for the best student paper. 19th Annual Conference On Learning Theory, COLT06.
  • "Prix ROSEMONT/DEMASSIEUX de la chancellerie des universités de Paris" Décembre 2008.
  • Miscellany

  • "Randomness is measurable." A. Kolmogorov
  • "There is nothing more practical than a good theory." K. Lewin.
  • "Genius is fifteen working hours a day." P. Valéry.