High-dimensional Bayesian Astronomical Imaging and Inverse Problems with Machine Learning
Abstract:
Recent progress in machine learning and generative modeling has opened new avenues to tackle previously insoluble high-dimensional inverse problems in astronomy and astrophysics, particularly in Bayesian image reconstruction. While these methodologies show great promise in a range of applications from field-level cosmology to differentiable optics systems, multiple open problems stand in the way of groundbreaking discoveries. This session will explore recent applications and proposals addressing the development of computationally tractable methodologies to reconstruct posterior samples in imaging problems. We will also discuss assessing their accuracy in real-world settings and addressing the problem of robustness to distributional shifts, which remains a key focus of current research.
Organiser & chair: Laurence Perreault Levasseur
Session Schedule
- 17:30 - 17:50
- Invited talk: Data-Driven High-Dimensional Inverse Problems: A Journey Through Strong Lensing Data Analysis and Other Imaging Inverse Problems
- Laurence Perreault-Levasseur
- 17:50 - 18:10
- Invited talk: Multimodal and Foundational Priors for Astronomical Inverse Problems
- François Lanusse
- 18:10 - 18:30
- Invited talk: Complex Galaxy Models with Conditional Score Models
- Peter Melchior
- 18:30 - 18:50
- Invited talk: 3D Imaging in Cosmology: From Dark Matter Mapping to Initial Conditions Reconstruction
- Carolina Cuesta
- 18:50 - 19:10
- Invited talk: Autoregressive Modelling in Simulation-Based Inference for High-Dimensional Cosmological Problems
- Noemi Montel*
- 19:10 - 20:30
- Invited poster: Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-Based Likelihoods and Priors
- Alexandre Adam*
- 19:10 - 20:30
- Invited poster: Toward Attaining the Diffraction Limit and Beyond in Astronomical Imaging
- Farzad Kamalabadi
- 19:10 - 20:30
- Contributed poster: Inverse-problem Versus Principal Component Analysis Methods for Angular Differential Imaging of Circumstellar Disk
- Sandrine Juillard*
- 19:10 - 20:30
- Contributed poster: Posterior Sampling for Solar Snapshot Spectroscopy with Score-Based Priors
- Ulas Kamaci*
- 19:10 - 20:30
- Contributed poster: Towards a Spherical Extension of the R2D2 Deep Neural Network Series Paradigm for Wide-field Radio Interferometric Imaging
- Ayoub Tajja*