The paper establishes an O(ε^{-4}) sample complexity bound for score estimation in diffusion models without requiring access to the empirical risk minimizer.
23 Published in Transactions on Machine Learning Research (04/2026) Combining the last three displays, E[L(θi+1)|θi]≤L(θi)−η∥∇L(θi)∥2 2 + Lη2 2 ( ∥∇L(θi)∥2 2 + σ2 bi )
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
-
Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access
The paper establishes an O(ε^{-4}) sample complexity bound for score estimation in diffusion models without requiring access to the empirical risk minimizer.