Context and objectives

The workshop on "Challenging problems in Statistical Learning" was held in Grenoble on March 17-18, 2011. This workshop aims to summarize the new and future problems in statistical learning and to give a good idea of what already exists for dealing with these problems. This event is co-organized by the University Paris 1 Panthéon-Sorbonne, INRIA Grenoble - Rhône-Alpes, Laboratoire Jean-Kuntzmann and the Statistics and Image group of the Société Française de Statistique.

The videos are now available (follow this link) and the slides can be downloaded below.

Thursday March 17, 2011

  • Session 1: Statistical learning and image analysis.
    • 09:30. Bach, Francis (INRIA Paris, Ecole Normale Supérieure)
      • Sparse Hierachical Dictionary Learning [slides.pdf]
    • 10:30. Coffee break
    • 11:00. Trouvé, Alain (CMLA, Ecole Normale Supérieure)
      • Shape analysis and computational anatomy: A geometrical perspective on the statistical analysis of population of manifolds [slides.pdf]
    • 12:00. Harchaoui, Zaid (INRIA Rhône-Alpes)
      • Learning from temporal data: some contributions and new challenges
  • Session 2: Statistical learning in high dimension.
    • 14:30. Verleysen, Michel (Université catholique de Louvain)
      • Information theoretic feature selection for non-standard data [slides.pdf]
    • 15:30. Coffee break
    • 16:00. Grandvalet, Yves (CNRS, UTC)
      • Sparsity in learning [slides.pdf]
    • 17:00. Celeux, Gilles, (INRIA Saclay)
      • Variable selection in model-based unsupervised and supervised classification [slides.pdf]

Friday March 18, 2011

  • Session 3: Statistical learning and structured data.
    • 08:30. Vert, Jean-Philippe (Mines ParisTech, Institut Curie)
      • Including prior knowledge in machine learning for genomic data [slides.pdf]
    • 09:30. Coffee break
    • 10:00. Archambeau, Cédric (Xerox Research Centre Europe)
      • Variational inference for partially observed diffusion processes [slides.pdf]
    • 11:00. Carreau, Julie (IRD, HydroSciences Montpellier)
      • Mixture of heavy-tailed distributions for bivariate precipitation data [slides.pdf]
  • Session 4: New and future problems in statistical learning.
    • 13:30. Antoniadis, Anestis (LJK, Université Joseph Fourier)
      • Regularizarion and shrinkage for model selection in sparse GLM models [slides.pdf]
    • 14:30. Coffee break
    • 15:00. François, Olivier (TIMC-IMAG, Grenoble INP)
      • Latent variable models in population genetics [slides.pdf]
    • 16:00. Verzelen, Nicolas (INRA Montpellier)
      • Minimax risks for sparse regressions: Ultra-high-dimensional phenomenons [slides.pdf]

Directions

The workshop will be held in Maison Jean Kuntzmann, MI2S-UMS 3042, Domaine Universitaire, 38400 Saint Martin d'Hères. Directions and maps can be found here.

Accomodation

On possible hotel is the Résidhotel Central'Gare (8 place de la gare, 38000 Grenoble, Tel: +33 (0) 4.76.50.77.88, Fax: +33 (0) 4.76.50.67.01. It is located near the train station. It has wifi access and air conditionning. The rooms are actually small flats (studio). When booking, please mention that you come for the Statlearn workshop.

Organization

The workshop is organized by:

with the support of: