Paris workshop on Bayesian Deep Learning for Cosmology and Time Domain Astrophysics

Session

Cosmology

Jun 23, 2022, 9:00 AM

Buffon Amphitheater (APC laboratory, Université Paris Cité)

110. Artificial Intelligence: a game-changer for large scale structure cosmology

Dr Tomasz Kacprzak (ETH Zurich)

6/23/22, 9:00 AM

In large scale structure cosmology, the information about the cosmological parameters governing the evolution of the universe is contained in the complex and rich structure of dark matter density field.
To date, this information was probed using simple human-designed statistics, such as the 2-pt functions, which are not guaranteed or expected to capture the full information content of the LSS...

114. The Extended LSST Astronomical Time Series Classification Challenge (ELAsTiCC) (cosmo4)

Gautham Narayan (University of Illinois at Urbana-Champaign)

6/23/22, 10:00 AM

Talk

135. Hybrid Physical-Neural ODEs for fast differentiable N-body Simulations (cosmo3)

Denise Lanzieri (Cosmostat, CEA Paris-Saclay)

6/23/22, 10:20 AM

113. COSMOPOWER: Deep Learning - accelerated Bayesian inference from next-generation cosmological surveys

Alessio Spurio Mancini (University College London)

Talk

65. Graph-Convolutional Neural Networks for large-scale structure clustering (cosmo2)

Dr Farida Farsian (Bologna University, INAF)

Cosmology

Talk

One of the most important challenges in modern Cosmology will be to deal with enormous amount of data which will be produced by future cosmological and astrophysical surveys. Therefore, new methodologies such as Artificial Intelligence and Deep Learning (DL) should come to play to handle the computational expensive operations, automation and extracting of non explored data features and...

83. Interpreting non-Gaussian posterior distributions of cosmological parameters with normalizing flows (cosmo42)

Cyrille Doux (Laboratoire de Physique Subatomique et de Cosmologie)

Cosmology

Talk

Modern cosmological experiments yield high-dimensional, non-Gaussian posterior distributions over cosmological parameters. These posteriors are challenging to interpret, in the sense that classical Monte-Carlo estimates of summary statistics, such as tension metrics, become numerically unstable. In this talk, I will present recent work where normalizing flows (NF) are used to obtain analytical...

85. Maximum-A-posteriori estimate with Deep generative NEtworks for Source Separation (MADNESS) (cosmo5)

Biswajit Biswas (APC)

Cosmology

Talk

Next-generation of astronomical surveys such as the Large Survey of Space and Time (LSST) and Euclid will collect massive amounts of data. It will present challenges not only because of the sheer volume of data but also because of its complexity. As these surveys will detect fainter objects, the increased object density will lead to more overlapping sources. In LSST, for example, we expect...

73. The Extended LSST Astronomical Time Series Classification Challenge (ELAsTiCC) (cosmo4)

Gautham Narayan (University of Illinois at Urbana-Champaign)

Cosmology

Talk

The original Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) established the gold-standard reference dataset of Rubin light curves and catalyzed the development of several deep learning algorithms for classification. However, to truly simulate LSST operations, we must simulate not light curves, *but real-time alert streams, complete with the contextual information...