International Conference on Machine Learning for Astrophysics 2nd Ed. - ML4ASTRO2

Session

Cosmology & Simulations

11 Jul 2024, 14:30

Aula Magna (Catania)

Conveners

Cosmology & Simulations: V

• Eva Sciacca (Istituto Nazionale di Astrofisica (INAF))

254. [INVITED] Symbolic regression and interpretable ML

Deaglan Bartlett

11/07/2024, 14:30

Oral Presentation

The drawback of the more traditional, numerical ML techniques is their opaqueness; it is not always clear what information is being used and how methods trained on (necessarily imperfect) simulations will perform when applied to real-world data. An alternative branch of ML — Symbolic Regression (SR) — has clear advantages in this regard. By searching for simple, analytic descriptions of the...

255. Accelerated inference with neural networks for CMB and LSS analyses

Boris Bolliet

11/07/2024, 15:10

Oral Presentation

We will present state-of-the-art machine learning based tools that can be interfaced with traditional Boltzmann and sampling codes to accelerate inference analyses of CMB and LSS data. We will show real life example with the CMBxLSS code class_sz used in ACT and SO collaboration pipelines.

278. Globular clusters' dynamical age determination based on machine learning performed on large number of detailed MOCCA simulations

Arkadiusz Hypki

11/07/2024, 15:30

Oral Presentation

MOCCA code is able to perform detailed numerical simulations of globular clusters of any size within a few days (http://moccacode.net). Because of its speed and a close agreement with N-body codes MOCCA code is perfect to perform a grid of simulations for various initial conditions. It is currently beyond the capabilities of any N-body codes. At this moment our MOCCA database consists of over...