Computational and statistical trade-offs in learning

Europe/Paris
Salle de Conférences Marilyn et James Simons (Le Bois-Marie)

Salle de Conférences Marilyn et James Simons

Le Bois-Marie

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

Abstracts
Poster
Participants
  • adel chaibi
  • Adil SALIM
  • Alain CELISSE
  • Alexander Buchholz
  • Alexandre d'Aspremont
  • Alexis Bismuth
  • Amir Sani
  • Anael Bonneton
  • Anastasia Podosinnikova
  • Andre MANOEL
  • Andrei Grinenko
  • Andres Hoyos Idrobo
  • Anil Goyal
  • Anna Korba
  • Anne-Laure Poite
  • Antoine Recanati
  • Anton Osokin
  • Antonin PENON
  • Arthur Mensch
  • Aurélien Decelle
  • Balamurugan Palaniappan
  • Bekhti Yousra
  • Benoit Baylin
  • Brault Romain
  • Christine Keribin
  • Christophe Dupuy
  • Christophe Giraud
  • Claire Vernade
  • Combes Richard
  • Dacunha-castelle Didier
  • Damien Garreau
  • Damien Scieur
  • DAVY AXEL
  • Dmitrii Ostrovskii
  • Dmitry Babichev
  • Draief Moez
  • Edouard Oyallon
  • Elisabeth Gassiat
  • Elisabeth Jasserand
  • Emile Contal
  • Emilie Kaufmann
  • Eric Tramel
  • Evgenii Chzhen
  • Fedor Goncharov
  • Francis Bach
  • Frédéric Barbaresco
  • Gael Varoquaux
  • Garvesh Raskutti
  • Gerard Kerkyacharian
  • goude yannig
  • Guillaume Obozinski
  • Hariprasad Kannan
  • Igor Colin
  • Isabelle Guyon
  • Jair Montoya
  • Jean-Baptiste Alayrac
  • Jean-Luc Bouchot
  • Joseph Salmon
  • julie josse
  • Julien Floquet
  • Kamalaker Dadi
  • Luc Briard
  • Lucas Claude
  • Léna Carel
  • Malo Huard
  • Marie-Liesse Cauwet
  • Mario Lucic
  • Martin Bompaire
  • Maryan Morel
  • Mathieu Andreux
  • Maxime Sangnier
  • mehdi Sebbar
  • Mensch Arthur
  • Michael Eickenberg
  • odalric-ambrym maillard
  • Ohad Shamir
  • Oliver Burkart
  • Pascal Germain
  • Philippe Cuvillier
  • Pierre Alquier
  • Puneet Dokania
  • Quentin Berthet
  • Raphaël Nedellec
  • Rémi Gribonval
  • Rémi Leblond
  • Sandra Astete
  • Sebastien Treguer
  • Senanayak Karri
  • Servane Gey
  • Shell Xu Hu
  • Shihui LI
  • Silvia Villa
  • Simon Lacoste-Julien
  • Stanislas Chambon
  • Stéphane Rivaud
  • Sylvain Arlot
  • Tatiana Shpakova
  • The Tien Mai
  • Tristan Mary-Huard
  • Vianney Perchet
  • Vincent Roulet
  • Vincent Thouvenot
  • WENJIE ZHENG
  • yang qiu
  • Yves Le Jan
    • mardi 22 mars
      • 09:00
        Café d'accueil
      • 1
        Ohad Shamir
        Trade-offs in Distributed Learning
        Transparents
      • 2
        Alain Celisse
        Using kernels to detect abrupt changes in time series
        Transparents
      • 12:00
        Déjeuner
      • 3
        Alexandre d'Aspremont
        Renegar's Condition Number and Compressed Sensing Performance
        Transparents
      • 4
        Emilie Kaufmann
        Optimal Best Arm Identification with Fixed Confidence
        Transparents
      • 15:30
        Pause café
      • 5
        Vianney Perchet
        Highly-Smooth Zero-th Order Online Optimization
        Transparents
    • mercredi 23
      • 09:00
        Café d'accueil
      • 6
        Garvesh Raskutti
        Algorithmic and statistical perspectives of randomized sketching for ordinary least-squares
        Transparents
      • 7
        Pierre Alquier
        On the Properties of Variational Approximations of Gibbs Posteriors
        Transparents
      • 12:00
        Déjeuner
      • 8
        Quentin Berthet
        Trade-offs in Statistical Learning
        Transparents
      • 9
        Remi Gribonval
        Projections, Learning, and Sparsity for Efficient Data Processing
        Transparents
      • 15:30
        Pause café
      • 10
        Silvia Villa
        Generalization properties of multiple passes stochastic gradient method
        Transparents