Les personnes qui possèdent un compte PLM-Mathrice sont invités à l'utiliser.

Computational and statistical trade-offs in learning

de au (Europe/Paris)
à Le Bois-Marie ( Salle de Conférences Marilyn et James Simons )
35, route de Chartres 91440 Bures-sur-Yvette
Description

COMPUTATIONAL AND STATISTICAL TRADE-OFFS IN LEARNING

Organized by: Sylvain Arlot (Université Paris-Sud, Paris-Saclay), Francis Bach (INRIA Paris), Alain Celisse (Université de Lille 1)

This workshop focuses on the computational and statistical trade-offs arising in various domains (optimization, statistical/machine learning).
This is a challenging question since it amounts to optimize the performance under limited computational resources, which is crucial in the large-scale data context.
One main goal is to identify important ideas independently developed in some communities that could benefit the others.


Speakers :

Pierre Alquier (ENSAE, Paris-Saclay)
Alexandre d'Aspremont (D.I., CNRS/ENS Paris)
Quentin Berthet (DPMMS, Cambridge Univ., UK)
Alain Celisse (Université de Lille 1)
Rémi Gribonval (INRIA, Rennes)
Emilie Kaufmann (CNRS, Lille)
Vianney Perchet (CREST, ENSAE Paris-Saclay)
Garvesh Raskutti (Wisconsin Institute for Discovery, Madison, USA)
Ohad Shamir (Weizmann Institute, Rehovot, Israel)
Silvia Villa (Istituto Italiano di Tecnologia, Genova & MIT, Cambridge, USA)

 

logos

Documents:
Contact Email: jasserand@ihes.fr Telephone: 0160926604
Go to day
  • mardi 22 mars 2016
    • 08:45 - 17:00 mardi 22 mars
      • 09:00 Café d'accueil 1h0'
      • 10:00 Ohad Shamir 1h0'
        Trade-offs in Distributed Learning
        Documents: Transparents pdf file
      • 11:00 Alain Celisse 1h0'
        Using kernels to detect abrupt changes in time series
        Documents: Transparents pdf file
      • 12:00 Déjeuner 1h30'
      • 13:30 Alexandre d'Aspremont 1h0'
        Renegar's Condition Number and Compressed Sensing Performance
        Documents: Transparents pdf file
      • 14:30 Emilie Kaufmann 1h0'
        Optimal Best Arm Identification with Fixed Confidence
        Documents: Transparents pdf file
      • 15:30 Pause café 30'
      • 16:00 Vianney Perchet 1h0'
        Highly-Smooth Zero-th Order Online Optimization 
        Documents: Transparents pdf file
  • mercredi 23 mars 2016
    • 09:00 - 17:00 mercredi 23
      • 09:00 Café d'accueil 1h0'
      • 10:00 Garvesh Raskutti 1h0'
        Algorithmic and statistical perspectives of randomized sketching for ordinary least-squares
        Documents: Transparents pdf file
      • 11:00 Pierre Alquier 1h0'
        On the Properties of Variational Approximations of Gibbs Posteriors
        Documents: Transparents pdf file
      • 12:00 Déjeuner 1h30'
      • 13:30 Quentin Berthet 1h0'
        Trade-offs in Statistical Learning
        Documents: Transparents pdf file
      • 14:30 Remi Gribonval 1h0'
        Projections, Learning, and Sparsity for Efficient Data Processing
        Documents: Transparents pdf file
      • 15:30 Pause café 30'
      • 16:00 Silvia Villa 1h0'
        Generalization properties of multiple passes stochastic gradient method
        
        Documents: Transparents pdf file