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...

Täydet tiedot

Bibliografiset tiedot
Päätekijät: De Bortoli, V, Mathieu, E, Hutchinson, M, Thornton, J, Teh, YW, Doucet, A
Aineistotyyppi: Conference item
Kieli:English
Julkaistu: Curran Associates 2023

Samankaltaisia teoksia