Name: PCCP Workshop Series : Bayesian Deep Learning for Cosmology and Gravitational waves
Start: 2020-03-04T14:00:00+01:00
End: 2020-03-06T17:00:00+01:00
Location: PCCP, APC laboratory, Université de Paris

lundi 2 mars 2020
mardi 3 mars 2020
mercredi 4 mars 2020
14:00 Welcome address George Smoot (Nobel prize 2006)
Welcome address George Smoot (Nobel prize 2006)
14:00 - 14:30
Room: Pierre-Gilles de Gennes Amphitheater
Contributions

14:00 Logistics information
14:30
14:30 - 15:10
Room: Pierre-Gilles de Gennes Amphitheater
Contributions

14:30 An Introduction to Bayesian Deep Learning - Frédéric Pennerath (CentraleSupélec)
15:10
15:10 - 15:50
Room: Pierre-Gilles de Gennes Amphitheater
Contributions

15:10 Star-galaxy separation via Gaussian Processes with Neural Network Dual Kernels - Imene Goumiri (llnl)

15:30 Detection of gravitational-wave signals from binary neutron star signals using machine learning - Marlin Benedikt Schäfer (Albert Einstein Institut Hannover (AEI Hannover))
15:50 Coffee break
Coffee break
15:50 - 16:10
Room: Pierre-Gilles de Gennes Amphitheater
16:10
16:10 - 16:50
Room: Pierre-Gilles de Gennes Amphitheater
Contributions

16:10 Deep learning dark matter map reconstructions and parameter inference with Dark Energy Survey data - Niall Jeffrey (École normale supérieure)

16:30 Neural networks estimation of the dense-matter equation of state from neutron-star observables - Filip Morawski (Nicolaus Copernicus Astronomical Center of the Polish Academy of Sciences)
16:50 1 min presentation of posters
1 min presentation of posters
16:50 - 17:10
Room: Pierre-Gilles de Gennes Amphitheater
17:10
17:10 - 17:50
Room: Pierre-Gilles de Gennes Amphitheater
Contributions

17:10 Bayesian analysis and Supernova Photometric Cosmology - Emille Ishida (LPC-UCA)
18:30 Cocktail Reception
Cocktail Reception
18:30 - 19:30
jeudi 5 mars 2020

09:00 Coffee and pastries
Coffee and pastries
09:00 - 09:30
Room: Buffon Amphitheater
09:30 Variational inference vs. MCMC
Variational inference vs. MCMC
09:30 - 11:00
Room: Buffon Amphitheater
Contributions

09:30 Tutorial: Bayesian deep learning - MCMC vs VI - Tom Charnock (IAP)
11:00 Coffee break and poster session
Coffee break and poster session
11:00 - 11:30
Room: Buffon Amphitheater

11:30 Variational inference vs. MCMC
Variational inference vs. MCMC
11:30 - 12:20
Room: Buffon Amphitheater

12:20 Lunch on your own
Lunch on your own
12:20 - 14:00
Room: Pierre-Gilles de Gennes Amphitheater
14:00 Google / TensorFlow Probability
Google / TensorFlow Probability
14:00 - 14:40
Room: Buffon Amphitheater
Contributions

14:00 TensorFlow Probability - Brian Patton (Google)
14:40
14:40 - 15:40
Room: Buffon Amphitheater
Contributions

14:40 Deep learning for a faster Hamiltonian Monte Carlo sampler - Marc Arène (APC)

15:00 Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning - Mike Walmsley (University of Oxford)

15:20 Bayesian parameter estimation using conditional variational autoencoders for gravitational wave astronomy - Hunter Gabbard (University of Glasgow)
15:40 Coffee break and poster session
Coffee break and poster session
15:40 - 16:10
Room: Buffon Amphitheater
16:10
16:10 - 17:10
Room: Buffon Amphitheater
Contributions

16:10 Denoising gravitational wave signals with a variational autoencoder - Philippe BACON (Laboratoire Astroparticule et Cosmologie)

16:30 Solving source separation problem for LISA data analysis with Autoencoders - Natalia Korsakova (Observatoire de la Côte d'Azur)

16:50 The devil is in the details: interpreting probabilities from machine learning - Alex Malz (German Centre of Cosmological Lensing)
17:10 Synergies between academia and tech companies: hardware, computing, algorithms and people
Synergies between academia and tech companies: hardware, computing, algorithms and people
17:10 - 18:00
Room: Buffon Amphitheater
vendredi 6 mars 2020
09:30 TensorFlow Probability
TensorFlow Probability
09:30 - 12:30
Contributions

09:30 TensorFlow Probability - Brian Patton, Junpeng Lao (TensorFlow Probability - Google)

11:10 TensorFlow Probability - Brian Patton, Junpeng Lao (TensorFlow Probability - Google)
12:30 Buffet @ Microsoft
Buffet @ Microsoft
12:30 - 14:00
Room: Pierre-Gilles de Gennes Amphitheater
14:00 Graphcore, Microsoft Azure, LightOn
Graphcore, Microsoft Azure, LightOn
14:00 - 15:35
Contributions

14:00 Graphcore: Innovation in Machine Intelligence Hardware & Software - Alexander Titterton (Graphcore)

14:45 Large-scale Machine Learning on LightOn’s Optical Processing Units - Laurent Daudet (Light On)

15:15 Microsoft Azure - Alexandre Jean (Microsoft)
15:35 Wrap-up
Wrap-up
15:35 - 16:00
Contributions

15:35 Organizers wrap-up
16:00 Coffee break and networking
Coffee break and networking
16:00 - 16:30