Generative models and component separations for physical fields with Scattering Transforms.

Erwan Allys, Sébastien Pierre, Alexandros Tsouros, Pablo Richard

Session: Energy- and score-based models (Joakim Andén)

Keywords: Maximum entropy model, Scattering Transform, Component separation

Abstract: Scattering transform statistics have led to recent advances in the modelling of physical processes. These statistics, which are inspired by neural networks but can be estimated without a training step, allow quantitative modelling of physical processes even from very small data sets in a maximum entropy framework. After introducing these models and demonstrating their quantitative validation on several examples, I will discuss how they can form the basis of new algorithms for inverse problems and component separation. In particular, I will show how they can be used to separate components even in a very limited data regime and without physically-driven priors of the component of interest, with examples of applications to astrophysical data.

Submission Number: 43