Séminaire Doctoral / Seminar PhD |
| « Galaxy/Halo bias modeling, a hybrid machine learning approach » |
|
Simon Ding |
| Accurately describing the relation between the dark matter over-density and the observable galaxy field is one of the significant obstacles to analyzing cosmic structures with next-generation galaxy surveys. Current galaxy bias models are either inaccurate or computationally too expensive to be used for efficient inference of small-scale information. To address this problem, in this talk, I will present a hybrid machine learning approach called the Neural Physical Engine (NPE) that was first developed and tested by Charnock et al. (2020). The network architecture exploits physical information of the galaxy bias problem and is suitable for zero-shot learning within field-level inference approaches. |
|
vendredi 2 décembre 2022 - 16:00 Salle du Conseil, Institut d'Astrophysique |
| Page web du séminaire / Seminar's webpage |