On Maximum Likelihood Training of Score-Based Generative Models

By Conor Durkan, Yang Song. 2021

13 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

Citations in the corpus

Score-based Generative Modeling in Latent Space (2021, methodology): “[2] show how this modeling approach is described with a stochastic differential equation (SDE) framework which can be converted to maximum likelihood training [4].”
A Variational Perspective on Diffusion-Based Generative Models and Score Matching (2021, methodology): “This suggests the likelihood of the equivalent ODE can be improved by minimizing the score matching loss, as the ODE’s likelihood will be close to plug-in reverse SDEs with λ ≈ 1 , which explains the good likelihood of the equivalent ODE reported in Song et al. (2021).”
Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling (2021, unknown): “…(2021); Gao et al. (2020); Jolicoeur-Martineau et al. (2021b); Ho et al. (2020); Song and Ermon (2020); Song et al. (2020, 2021); Niu et al. (2020); Durkan and Song (2021); Hoogeboom et al. (2021); Saharia et al. (2021); Luhman and Luhman (2021, 2020); Nichol and Dhariwal (2021); Popov et al.…”
Riemannian Score-Based Generative Modeling (2022, methodology): “Finally, we note that there exist other approaches to introduce SGMs using variational and maximum likelihood techniques (Ho et al., 2020; Huang et al., 2021; Durkan and Song, 2021).”
Score Matching Model for Unbounded Data Score (2021, background): “[Theorem 2 of [46]] Assuming log p t ( x ) and log q t ( x ) are smooth functions which have at most polynomial growth at the inﬁnity and p T = π , where π is the prior distribution, we have Remark 1 .”