Reviews: A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks

In population genetics, a common problem is the inference of evolutionary events and parameters given some observed DNA sequencing data. This is typically done by leveraging genetic simulators based on the coalescence model. For example, in approximate Bayesian Computation (ABC) one can infer the posterior distribution of the evolutionary parameter of interest by (i) drawing its value from a prior, (ii) generate population genetic data from a simulator using the drawn parameter value and (iii) weight the importance of the sample based on the similarity between the simulated and the real data. Similarity is typically defined in terms of a pre-chosen set of summary statistics. The authors propose an inference strategy that does not rely on any choice of summary statistics.