Join us this Friday, June 5th at 3pm exclusively on zoom for the final meeting of the Stats and ML Journal Club for the quarter. This week, I (Sean McLaughlin) will lead a discussion on GalaxyNet, a new approach to modeling galaxy occupation. See you then!

Title: GalaxyNet: Connecting galaxies and dark matter haloes with deepneural networks and reinforcement learning in large volumes
Abstract: We present the novel wide & deep neural network GalaxyNet, which connects the properties
of galaxies and dark matter haloes, and is directly trained on observed galaxy statistics using
reinforcement learning. The most important halo properties to predict stellar mass and star
formation rate (SFR) are halo mass, growth rate, and scale factor at the time the mass peaks,
which results from a feature importance analysis with random forests. We train different
models with supervised learning to find the optimal network architecture. GalaxyNet is then
trained with a reinforcement learning approach: for a fixed set of weights and biases, we
compute the galaxy properties for all haloes and then derive mock statistics (stellar mass
functions, cosmic and specific SFRs, quenched fractions, and clustering). Comparing these
statistics to observations we get the model loss, which is minimised with particle swarm
optimisation. GalaxyNet reproduces the observed data very accurately (χred = 1.05), and
predicts a stellar-to-halo mass relation with a lower normalisation and shallower low-mass
slope at high redshift than empirical models. We find that at low mass, the galaxies with the
highest SFRs are satellites, although most satellites are quenched. The normalisation of the
instantaneous conversion efficiency increases with redshift, but stays constant above z & 0.7.
Finally, we use GalaxyNet to populate a cosmic volume of (5.9 Gpc)
3 with galaxies and predict
the BAO signal, the bias, and the clustering of active and passive galaxies up to z = 4, which
can be tested with next-generation surveys, such as LSST and Euclid.