Showing 2020Show all
2 papers · 1 filter
math.AG2020
Sampling and homology via bottlenecks
Sandra Di Rocco, David Eklund, Oliver Gäfvert
In this paper we present an efficient algorithm to produce a provably dense sample of a smooth compact variety. The procedure is partly based on computing of…
cs.LG2020
Variational Autoencoders with Riemannian Brownian Motion Priors
Dimitris Kalatzis, David Eklund, Georgios Arvanitidis +1
Variational Autoencoders (VAEs) represent the given data in a low-dimensional latent space, which is generally assumed to be Euclidean. This assumption naturally leads to the commo…