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

Session

ML Methodology

22 juin 2022, 09:00

Buffon Amphitheater (APC laboratory, Université Paris Cité)

107. Scalable Bayesian Workflows in JAX

Colin Carroll (Google)

22/06/2022 09:00

100. Fast Inference of Star Formation Histories of Galaxies with Spectra and Simulation-Based Inference (SBI) (sbi2)

Gourav Khullar (Dept of Astronomy and Astrophysics, Kavli Institute for Cosmological Physics (KICP), University of Chicago)

22/06/2022 10:00

Talk

101. HARMONIC: Bayesian model comparison for simulation-based inference (methods1)

Matthew Docherty (UCL)

22/06/2022 10:20

106. Enhancing gravitational-wave population inference with deep learning (sbi1)

Matthew Mould (University of Birmingham)

22/06/2022 11:20

Talk

134. Neural Posterior Estimation with Differentiable Simulators (methods2)

Justine Zeghal (APC)

22/06/2022 11:40

Talk

102. Amortized variational inference for supernovae light curves (methods3)

Alexis Sánchez (Universidad de Concepción)

22/06/2022 12:00

Talk

103. Self-Supervised Machine Learning; Detecting Galaxy Tidal Features in HSC-SSP (methods4)

Alice Desmons (UNSW Sydney)

22/06/2022 12:20

Talk

79. Amortized variational inference for supernovae light curves (methods3)

Alexis Sánchez (Universidad de Concepción)

ML Methodology

Talk

Markov Chain Monte Carlo (MCMC) methods are widely used for Bayesian inference in astronomy. However, when applied to data coming from next-generation telescopes, inference requires a significant amount of resources. An alternative is to use amortized variational inference, which consists of introducing a function that maps the observations to the parameters of an approximate posterior...

60. Enhancing gravitational-wave population inference with deep learning (sbi1)

Matthew Mould (University of Birmingham)

Simulation based Inference

Talk

Gravitational-wave population studies have become a common approach to learn about the astrophysical distribution of merging stellar-mass binary black holes. The goal is to map the source properties (e.g., masses and spins) of events observed by ground-based interferometers --which have been filtered through detection biases-- to the true parameter distributions as a whole across the...

68. Fast Inference of Star Formation Histories of Galaxies with Spectra and Simulation-Based Inference (SBI) (sbi2)

Gourav Khullar (Dept of Astronomy and Astrophysics, Kavli Institute for Cosmological Physics (KICP), University of Chicago)

Simulation based Inference

Talk

A pressing question in the field of cosmological structure formation is how the long-term assembly and evolution of baryonic matter occurs in galaxies. Galaxies take different pathways to assemble their stellar mass, signatures of which can be derived from galaxy star formation histories via stellar population synthesis (SPS) modeling. Today, we are approaching the age of trillion-galaxy...

71. HARMONIC: Bayesian model comparison for simulation-based inference (methods1)

Matthew Docherty (UCL)

ML Methodology

Talk

Simulation-based inference techniques will play a key role in the analysis of upcoming astronomical surveys, providing a statistically rigorous method for Bayesian parameter estimation. However, these techniques do not provide a natural way to perform Bayesian model comparison, as they do not have access to the Bayesian model evidence.

In my talk I will present a novel method to estimate...

80. Self-Supervised Machine Learning; Detecting Galaxy Tidal Features in HSC-SSP (methods4)

Alice Desmons (UNSW Sydney)

ML Methodology

Talk

With the advent of the Rubin Observatory's Legacy Survey of Space and Time (LSST), which will reach the petabyte data regime, it is imperative that we refine our methods of detecting and classifying images of interest within this myriad of data. In this talk I will present promising results from a Self-Supervised Machine Learning Algorithm, specifically the SimSiam Contrastive Learning model,...