Pour vous authentifier, privilégiez eduGAIN / To authenticate, prefer eduGAIN

RAMP 03 Astrophyiscs



200 rue André Ampère 91 440 Bures-sur-Yvette
Akin Kazakci (MINES ParisTech), Alexandre Gramfort (Telecom ParisTech, CNRS), Balázs Kégl (LAL), Djalel Benbouzid (LAL, Université Paris-Sud), Loïc Estève (INRIA)

This RAMP will be on Astrophysics, more precisely, on classification of variable stars from their light curves (luminosity vs time profiles), brought to you by Marc Monier (LAL), Gilles Faÿ (Centrale-Supelec), and your regular coaches.

The event will take place at Proto204, a 10 minute walk from either the Orsay-Ville or the Bur-sur-Yvette RER B stations.

Supporting material:

Some general guidelines. 

Your primary goal is to have a high score in the "contributivity" column. One way to achieve it is to submit a strong model, high in the "score" column, but we appreciate especially those models which do not have top scores but are sufficiently different from the rest of the models to achieve high score in the "contributivity" column.

Our best feature extractor is based on Gaussian Process. It smoothes the light curves, aligns them so the period starts at the minimum luminosity, normalizes the amplitude so the response is bounded between 0 and 1, and bins the smooth curve into ten bins. It also adds the amplitude and the lenght scale (smoothness) as feature. Here are some plots that show how it works.

The performance gain is significant, so you might want to work on this model if you decide to improve the feature extractor. The bad news is that it is quite slow: it takes eight minutes to train. So, if you submit anything based on this feature extractor, please do extensive preliminary tests on your computer or on your private VM, and do not submit more than once per 30 minutes to an hour. A general rule is that you should not resubmit until your previous model has not yet been trained (it shows up in the "New models" table.)

Some strategies you can employ:

  1. Take a good classifier and work on the feature extractor or vice verse.
  2. Take a good classifier or feature extractor and optimize its hyperparameters using smac or hyperopt. See the course material for help.
  3. Take two good submissions and combine the feature extractor and the classifier.
  • Adrien PAIN
  • Alexandre Beelen
  • Alexandre Boucaud
  • Amir Sani
  • anaelle pain
  • Anais Möller
  • Anastase Charantonis
  • Antoine Bureau
  • Antoine Pérus
  • asma atamna
  • Aurelie MUTSCHLER
  • Basile mayeur
  • Bogdan-Ionut Cirstea
  • Christian Arnault
  • Delphine Le
  • Eric TUON
  • Farhang Habibi
  • François-David Collin
  • Gaetan Marceau Caron
  • Giannis Bekoulis
  • Hervé Bertin
  • Isabelle Guyon
  • Izzet Burak Yildiz
  • Jean Lafond
  • Kevin Lourd
  • Lionel LIMERY
  • liying wei
  • Maria Rossi
  • mehdi cherti
  • mehdi sebbar
  • michael blot
  • nacim belkhir
  • Naveen Kumar Aranganathan
  • Odalric-Ambrym Maillard
  • Pierre-Yves Massé
  • Rafael Morales
  • Rémi Bardenet
  • Sana Tfaili
  • Sourava Prasad Mishra
  • Thomas Schmitt
  • Tien PHAN
    • 9:00 AM 9:30 AM
      Welcome of participants & Coffee
    • 9:30 AM 10:00 AM
      Introduction talk
    • 10:00 AM 12:00 PM
      Data munging and machine learning session 1
    • 12:00 PM 1:30 PM
      Buffet & presentation of the first results
    • 1:30 PM 3:00 PM
      Data munging and machine learning session 2
    • 3:00 PM 3:30 PM
    • 3:30 PM 5:00 PM
      Data munging and machine learning session 3
    • 5:00 PM 6:00 PM
      Debriefing and closing