61 citations · 101 across the 6 of their papers we have counts for
7 papers
Simplex Diffusion Models
Justin Deschenaux, Alexandre Galashov, Andrew Campbell +4
Diffusion models have revolutionized generative modeling for continuous data through the gradual refinement of a belief state. This iterative refinement has not yet carried over to…
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 `…
Simulating Diffusion Bridges with Score Matching
Jeremy Heng, Valentin De Bortoli, Arnaud Doucet +1
We consider the problem of simulating diffusion bridges, which are diffusion processes that are conditioned to initialize and terminate at two given states. The simulation of diffu…
Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
Valentin De Bortoli, James Thornton, Jeremy Heng +1
Progressively applying Gaussian noise transforms complex data distributions to approximately Gaussian. Reversing this dynamic defines a generative model. When the forward noising p…
Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
Adrien Corenflos, James Thornton, George Deligiannidis +1
Particle Filtering (PF) methods are an established class of procedures for performing inference in non-linear state-space models. Resampling is a key ingredient of PF, necessary to…