Riemannian score-based generative modelling
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 noising'' stage, whereby a diffusion is used to gradually add Gaussian noise to data, and a generative model, wh...
Main Authors: | De Bortoli, V, Mathieu, E, Hutchinson, M, Thornton, J, Teh, YW, Doucet, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Curran Associates
2023
|
Similar Items
-
Diffusion Schrödinger bridge with applications to score-based generative modeling
by: De Bortoli, V, et al.
Published: (2022) -
Generative models as distributions of functions
by: Dupont, E, et al.
Published: (2022) -
Riemannian geometry/
by: 415273 Eisenhart, Luther Pfahler
Published: (1949) -
On the space of Riemannian metrics
by: Ebin, David Gregory, 1942-
Published: (2009) -
Differential and Riemannian geometry/
by: 331499 Laugwitz, Detlef, et al.
Published: (1965)