Reliable ABC model choice via random forests

368 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Efficient ancestry and mutation simulation with msprime 1.0 (2021, methodology): “Modern approaches to ABC such as ABC-RF (Pudlo et al. 2016; Raynal et al. 2019) and ABC-NN (Blum and Franc¸ois 2010; Csill (cid:2) ery et al. 2012) use large numbers of weakly informative statistics, making the need to efficiently compute statistics from simulation results all the more acute.”
Supervised Machine Learning for Population Genetics: A New Paradigm (2018, background): “For instance, it was recently shown [63] that random forests outperform ABC in both accuracy and computational cost when performing demographic model selection, together with greater robustness to the choice of summary statistics included in the input vector.”