61 citations · 101 across the 6 of their papers we have counts for
3 papers · 1 filter
Riemannian Diffusion Schrödinger Bridge
James Thornton, Michael Hutchinson, Emile Mathieu +3
Score-based generative models exhibit state of the art performance on density estimation and generative modeling tasks. These models typically assume that the data geometry is flat…
Rethinking Initialization of the Sinkhorn Algorithm
James Thornton, Marco Cuturi
While the optimal transport (OT) problem was originally formulated as a linear program, the addition of entropic regularization has proven beneficial both computationally and stati…
Riemannian Score-Based Generative Modelling
Valentin De Bortoli, Emile Mathieu, Michael Hutchinson +3
Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance. Score-based generative modelling (SGM) consists of a `…