Posterior sampling under a generative prior can be performed by training a diffusion model in the generator's noise space and pushing its samples through the generator.
Amortized methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
Posterior sampling under a generative prior can be performed by training a diffusion model in the generator's noise space and pushing its samples through the generator.