Fast, flexible, and accurate evaluation of Malmquist bias for Advanced LIGO/Virgo and beyond.

Understanding and modeling observational selection effects is vital to performing unbiased inference with observed astrophysical populations. Current methods used to estimate the selection function for compact binaries in gravitational-wave transient surveys at sufficient precision will become computational impractical as the observed catalog continues to grow. In this talk, I will describe how we can leverage machine learning techniques to increase our precision while reducing the computational cost.