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

Europe/Paris
Pierre-Gilles de Gennes Amphitheater (PCCP, APC laboratory, Université de Paris)

Pierre-Gilles de Gennes Amphitheater

PCCP, APC laboratory, Université de Paris

10 Rue Alice Domon et Léonie Duquet, 75013 Paris
Description

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
Registration form
Participants
  • Agata Trovato
  • Aishik Ghosh
  • Alan Heavens
  • Alex Malz
  • Alexander Tanaka
  • Alexandre Boucaud
  • Alexandre Jean
  • Alvina Burgazli
  • Amedeo Napoli
  • Andrew Miller
  • Atul Divakarla
  • Axel Journe
  • Bastien Arcelin
  • Boris Leistedt
  • Brian Patton
  • Brieuc Conan Guez
  • Calum Murray
  • Christophe Le Poncin-Lafitte
  • Claire Theobald
  • Cyril Cano
  • Cécile Roucelle
  • Dan Piponi
  • Daniela Saadeh
  • David Maurin
  • Dongwon Han
  • Ed Porter
  • Emille Ishida
  • Eric Aubourg
  • Eric Chassande-Mottin
  • Eric Hivon
  • Fangchen FENG
  • Filip Morawski
  • Florent Robinet
  • François Lanusse
  • Frédéric Pennerath
  • Grégory Baltus
  • Guilhem Lavaux
  • Gwenhaël de Wasseige
  • Hector Hortua
  • Henri Inchauspé
  • Hubert Bretonniere
  • Hunter Gabbard
  • Imene Goumiri
  • Ioannis Michaloliakos
  • Jerome Bobin
  • Junpeng Lao
  • Ken Ganga
  • Marc Arène
  • Marko Shuntov
  • Marlin Benedikt Schäfer
  • Martin KILBINGER
  • Maude Le Jeune
  • Michael Williams
  • Michał Bejger
  • Miguel Couceiro
  • Mike Walmsley
  • Mukharbek Organokov
  • Natalia Korsakova
  • Niall Jeffrey
  • Nikolaos Karnesis
  • Océane Dhuicque
  • Pablo Lemos
  • Philippe Bacon
  • Qitong Wang
  • Simona Mei
  • Stéphane Ilic
  • Swetha Bhagwat
  • Themis Palpanas
  • Tilman Troester
  • Tom Charnock
  • Vincent Boudart
    • 14:00 14:30
      Organisers: Welcome address George Smoot (Nobel prize 2006) Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
    • 14:30 15:10
      Invited talk Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
      • 14:30
        An Introduction to Bayesian Deep Learning 40m

        Bayesian Deep Learning (BDL) fills an important gap in the current deep neural networks, no matter powerful they are: in figurative terms, one could say BDL gives to AI the introspective ability to assess its own level of ignorance due to a lack of observations.
        In more technical terms, BDL adopts the view of Bayesian statistics by replacing the weights of neural networks by distributions.
        While this idea is nothing new, BDL has recently undergone new developments, thanks in particular to the seminal work of Y. Gal.
        This presentation is designed to be a gentle introduction of the main concepts of BDL.
        It introduces the required notions of Deep Learning and Bayesian statistics before developing the BDL framework.
        It will not assume any particular piece of knowledge, but some general notions in machine Learning and Neural Networks.

        Speaker: Frédéric Pennerath (CentraleSupélec)
    • 15:10 15:50
      Contribution talks Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
      • 15:10
        Star-galaxy separation via Gaussian Processes with Neural Network Dual Kernels 20m
        Speaker: Dr Imene Goumiri (llnl)
      • 15:30
        Detection of gravitational-wave signals from binary neutron star signals using machine learning 20m
        Speaker: Marlin Benedikt Schäfer (Albert Einstein Institut Hannover (AEI Hannover))
    • 15:50 16:10
      Coffee break 20m Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
    • 16:10 16:50
      Contribution talks Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
      • 16:10
        Deep learning dark matter map reconstructions and parameter inference with Dark Energy Survey data 20m
        Speaker: Dr Niall Jeffrey (École normale supérieure)
      • 16:30
        Neural networks estimation of the dense-matter equation of state from neutron-star observables 20m
        Speaker: Mr Filip Morawski (Nicolaus Copernicus Astronomical Center of the Polish Academy of Sciences)
    • 16:50 17:10
      Lightning talks: 1 min presentation of posters Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris

      PhD or postdocs present quickly their work

    • 17:10 17:50
      Invited talk Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
      • 17:10
        Bayesian analysis and Supernova Photometric Cosmology 40m

        In the end of the 20th century type Ia supernovae provided the first evidence for accelerated cosmic expansion -- completely changing the cosmological model paradigm. Since then, the astronomical community has devote much of its resources to the construction of large scale sky surveys which are expected to achieve first light in the next few years. The upcoming Large Survey of Space and Time at the Vera Rubin Observatory (LSST) is one of the most ambitious of such experiments. In the new data paradigm raised by the next generation of surveys, which will deliver larger and more complex astronomical data than ever before, the methods of data analysis will need to be adapted to the new reality. In this talk, I will briefly describe the traditional pipeline for supernova cosmology, highlighting the new challenges to be faced and list a number of potential improvements already achieved by the application of Bayesian analysis. In particular, I will focus on how the combination of Bayesian techniques with adaptive machine learning algorithms can enable purely photometric supernova cosmology in the next decade.

        Speaker: Dr Emille Ishida (LPC-UCA)
    • 18:30 19:30
      Cocktail Reception 1h Barge du CROUS

      Barge du CROUS

      Quai François Mauriac, Port de la Gare, 75013 Paris
    • 09:00 09:30
      Coffee and pastries 30m Buffon Amphitheater (Université de Paris - Campus des Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus des Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
    • 09:30 11:00
      Tutorial: Variational inference vs. MCMC Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
    • 11:00 11:30
      Coffee break and poster session 30m Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
    • 11:30 12:20
      Round table: Variational inference vs. MCMC Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris

      Academia has a tradition of fostering interaction between scientific fields but not with companies. In the past years, we have witnessed a development of academic-type research teams within big tech companies, especially in machine learning. As machine learning is becoming a very hot topic in Physics (and quantum computing might also), we need these kind of interactions more than ever. How can we make those two worlds benefit from each other?

      Conveners: Boris Leistedt (Imperial College), Edward Porter (APC/CNRS), François Lanusse (CEA/AIM), Junpeng Lao (Google), Tom Charnock (IAP)
    • 12:20 14:00
      Lunch on your own 1h 40m Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
    • 14:00 14:40
      Invited talk: Google / TensorFlow Probability Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
      • 14:00
        TensorFlow Probability 40m
        Speaker: Brian Patton (Google)
    • 14:40 15:40
      Contribution talks Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
    • 15:40 16:10
      Coffee break and poster session 30m Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
    • 16:10 17:10
      Contribution talks Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris
      • 16:10
        Denoising gravitational wave signals with a variational autoencoder 20m
        Speaker: Dr Philippe BACON (Laboratoire Astroparticule et Cosmologie)
      • 16:30
        Solving source separation problem for LISA data analysis with Autoencoders 20m
        Speaker: Dr Natalia Korsakova (Observatoire de la Côte d'Azur)
      • 16:50
        The devil is in the details: interpreting probabilities from machine learning 20m
        Speaker: Alex Malz (German Centre of Cosmological Lensing)
    • 17:10 18:00
      Round table: Synergies between academia and tech companies: hardware, computing, algorithms and people Buffon Amphitheater (Université de Paris - Campus Grands Moulins)

      Buffon Amphitheater

      Université de Paris - Campus Grands Moulins

      15 Rue Hélène Brion, 75013 Paris

      Academia has a tradition of fostering interaction between scientific fields but not with companies. In the past years, we have witnessed a development of academic-type research teams within big tech companies, especially in machine learning. As machine learning is becoming a very hot topic in Physics (and quantum computing might also), we need these kind of interactions more than ever. How can we make those two worlds benefit from each other?

      Conveners: Alexandre Jean (Microsoft), Eric Aubourg (APC), Eric Chassande-Mottin (CNRS AstroParticule et Cosmologie), Laurent Daudet (Lighton), Marco Cuturi (Google), Volker Beckmann (CNRS / IN2P3)
    • 09:30 12:30
      Tutorial: TensorFlow Probability Microsoft France

      Microsoft France

      41 Quai du Président Roosevelt, 92130 Issy-les-Moulineaux
    • 12:30 14:00
      Buffet @ Microsoft 1h 30m Pierre-Gilles de Gennes Amphitheater

      Pierre-Gilles de Gennes Amphitheater

      PCCP, APC laboratory, Université de Paris

      10 Rue Alice Domon et Léonie Duquet, 75013 Paris
    • 14:00 15:35
      Invited talk: Graphcore, Microsoft Azure, LightOn Microsoft France

      Microsoft France

      41 Quai du Président Roosevelt, 92130 Issy-les-Moulineaux
      • 14:00
        Graphcore: Innovation in Machine Intelligence Hardware & Software 45m
        Speaker: Alexander Titterton (Graphcore)
      • 14:45
        Large-scale Machine Learning on LightOn’s Optical Processing Units 30m
        Speaker: Laurent Daudet (Light On)
      • 15:15
        Microsoft Azure 20m
        Speaker: Alexandre Jean (Microsoft)
    • 15:35 16:00
      Organisers: Wrap-up Microsoft France

      Microsoft France

      41 Quai du Président Roosevelt, 92130 Issy-les-Moulineaux
      • 15:35
        Organizers wrap-up 15m
    • 16:00 16:30
      Coffee break and networking 30m Microsoft France

      Microsoft France

      41 Quai du Président Roosevelt, 92130 Issy-les-Moulineaux