Skip to content
conftrace_
2025 ICML ICML 2025

Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Haoye Lu, Qifan Wu, Yaoliang Yu

Topics

Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Models > Diffusion Models Deep Learning > Techniques > Pretraining

Keywords

pretraining diffusion model noisy dataset cifar-10 deconvolution fid
Download PDF