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...
主要な著者: | De Bortoli, V, Mathieu, E, Hutchinson, M, Thornton, J, Teh, YW, Doucet, A |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Curran Associates
2023
|
類似資料
-
Diffusion Schrödinger bridge with applications to score-based generative modeling
著者:: De Bortoli, V, 等
出版事項: (2022) -
Generative models as distributions of functions
著者:: Dupont, E, 等
出版事項: (2022) -
Riemannian geodesics of semi Riemannian warped product metrics
著者:: Oriella M. Amici, 等
出版事項: (2013-01-01) -
Riemannian geometry /
著者:: Gallot, S. (Sylvestre), 1948-, 等
出版事項: (2004) -
Dynamically generated inflation from non-Riemannian volume forms
著者:: D. Benisty, 等
出版事項: (2019-09-01)