Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
Ambient diffusion: Learning clean distributions from corrupted data
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2representative citing papers
SFBD Flow converts the iterative SFBD approach into a continuous optimization framework for diffusion models on noisy samples, with its Online SFBD instantiation outperforming baselines.
citing papers explorer
-
Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
-
SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples
SFBD Flow converts the iterative SFBD approach into a continuous optimization framework for diffusion models on noisy samples, with its Online SFBD instantiation outperforming baselines.