Abstract

Dark matter halos are the fundamental building blocks of cosmic large-scale structure. Improving our theoretical understanding of their structure, evolution and formation is an essential step towards understanding how galaxies form. I will present a machine learning approach which aims to provide new physical insights into the physics driving halo formation. We train a machine learning algorithm to learn the relationship between the initial conditions and the final dark matter halos directly from N-body simulations. We evaluate the predictive performance of the algorithm when provided with different types of information about the initial conditions, allowing us to infer which aspects of the early-Universe density field impact the formation of the final dark matter halos. I will also present ongoing work which extends our method to deep learning algorithms, able to extract directly from the initial density field the features that are relevant to halo formation.