14:00 – 15:00 –Tom Nye (Newcastle University)
Title: Bayesian inference for kernels of Brownian motion in phylogenetic tree space
Abstract: Billera-Holmes-Vogtmann (BHV) tree space is a geometric space containing every possible evolutionary tree on a fixed set of taxa. Constructing parametric families of distributions on BHV tree space is very challenging due to its complex structure. We describe Bayesian methods for fitting transition kernels of Brownian motion, which are analogs of standard Gaussian distributions, to samples of points in BHV tree space. A non-Euclidean bridge construction lies at the heart of the approach.
Refreshments available between 15:00 – 15:30, Huxley Common Room (HXLY 549)