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...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: De Bortoli, V, Mathieu, E, Hutchinson, M, Thornton, J, Teh, YW, Doucet, A
Định dạng: Conference item
Ngôn ngữ:English
Được phát hành: Curran Associates 2023