Robust marginalization of baryonic effects for cosmological inference at the field level

We train neural networks to perform likelihood-free inference from (25,h-1rm Mpc)2 2D maps containing the total mass surface density from thousands of hydrodynamic simulations of the CAMELS project. We show that the networks can extract information beyond one-point functions and power spectra from all resolved scales (gtrsim 100,h-1rm kpc) while performing a robust marginalization over baryonic physics at the field level: the model can infer the value of Omegarm m (± 4%) and σ8 (± 2.5%) from simulations completely different to the ones used to train it.