Variational phylogenetic inference with products over bipartitions
This provides a more efficient method for Bayesian phylogenetic inference, which is important for evolutionary biologists analyzing genomic data.
The authors tackled the problem of approximating posterior distributions over phylogenetic trees by developing a variational Bayesian approach for ultrametric trees, achieving competitive accuracy with significantly fewer gradient evaluations than state-of-the-art methods.
Bayesian phylogenetics requires accurate and efficient approximation of posterior distributions over trees. In this work, we develop a variational Bayesian approach for ultrametric phylogenetic trees. We present a novel variational family based on coalescent times of a single-linkage clustering and derive a closed-form density of the resulting distribution over trees. Unlike existing methods for ultrametric trees, our method performs inference over all of tree space, it does not require any Markov chain Monte Carlo subroutines, and our variational family is differentiable. Through experiments on benchmark genomic datasets and an application to SARS-CoV-2, we demonstrate that our method achieves competitive accuracy while requiring significantly fewer gradient evaluations than existing state-of-the-art techniques.