PCCP Workshop Series : Bayesian Deep Learning for Cosmology and Gravitational waves

PCCP, APC laboratory, Université de Paris

PCCP, APC laboratory, Université de Paris

10 Rue Alice Domon et Léonie Duquet, 75013 Paris

Machine learning attracts a lot of interest in the fields of cosmology and gravitational-wave astronomy and may potentially lead to major breakthroughs. Its adoption by the scientific community is increasing dramatically but it does not yet belong to the toolbox of 'off-the-shelf' algorithms. One of the reasons is that built-in uncertainty estimation, which is core to the evaluation of any scientific measurement and analysis, is not yet common in machine learning models.

Such limitation is on the verge to be overcome by the emergence of probabilistic machine learning models and algorithms. Among them, recent models called Bayesian neural networks, which combine machine learning and Bayesian statistics, use new (deep) neural networks architectures to enable Bayesian inference, and have received a great attention from the artificial intelligence community over the past few years.

This workshop will give the participants the opportunity to learn more about these emerging methods and how to use and exploit them in their research. The workshop program includes invited lectures and tutorials from major computer science experts and contributed talk and poster session aimed at sharing experience between physicists on the practical applications of machine learning.


The workshop is intended to researchers and students that are familiar with machine learning, use this type of algorithms for their own work, and want to learn about the advanced techniques related to Bayesian deep learning.

Registration form
  • Agata Trovato
  • Aishik Ghosh
  • Alan Heavens
  • Alexander Tanaka
  • Alexandre Boucaud
  • Alvina Burgazli
  • Axel Journe
  • Bastien Arcelin
  • Brian Patton
  • Calum Murray
  • Christophe Le Poncin-Lafitte
  • Cyril Cano
  • Cécile Roucelle
  • Dan Piponi
  • David Maurin
  • Ed Porter
  • Emille Ishida
  • Eric Chassande-Mottin
  • Eric Hivon
  • Fangchen FENG
  • Filip Morawski
  • Florent Robinet
  • Grégory Baltus
  • Gwenhaël de Wasseige
  • Henri Inchauspé
  • Hubert Bretonniere
  • Hunter Gabbard
  • Jerome Bobin
  • Junpeng Lao
  • Ken Ganga
  • Martin KILBINGER
  • Maude Le Jeune
  • Mike Walmsley
  • Mukharbek Organokov
  • Nikolaos Karnesis
  • Océane Dhuicque
  • Pablo Lemos
  • Philippe Bacon
  • Qitong Wang
  • Simona Mei
  • Stéphane Ilic
  • Swetha Bhagwat
  • Themis Palpanas
  • Tom Charnock
  • Vincent Boudart
    • 14:00 14:30
      Welcome: address George Smoot (Nobel prize 2006)
    • 14:30 15:10
      Invited talk

      Introduction to bayesian neural network by invited speaker from computer science community

    • 15:10 15:50
      Contribution talks
    • 15:50 16:10
      Coffee break 20m
    • 16:10 16:50
      Contribution talks
    • 16:50 17:50
      Round table
    • 09:00 12:20
      Variational inference VS. MCMC: Tutorial and round table
      • 09:00
        Tutorial: overview of the differences between MCMC and Variational Inference 2h
        Speaker: Dr Tom Charnock (IAP)
      • 11:00
        Coffee break 20m
      • 11:20
        round table: Variational inference VS. MCMC 1h
    • 14:00 14:40
      Invited talk: Google / TensorFlow Probability

      Introduction to bayesian neural network by invited speaker from computer science community

    • 14:40 15:30
      Lightning talks

      PhD or postdocs present quickly their work

    • 15:30 15:50
      Coffee break 20m
    • 15:50 17:30
      Contribution talks
    • 09:00 12:00
      Tutorial: TensorFlow Probability - Josh Dillon (Software engineer at Google)
    • 14:00 16:00
      Invited talk: Deep learning on the cloud : Microsoft Azure, Google Colab

      Introduction to bayesian neural network by invited speaker from computer science community