The paper establishes an O(ε^{-4}) sample complexity bound for score estimation in diffusion models without requiring access to the empirical risk minimizer.
Substituting this into (108) gives E [ L(θT )−L⋆] ≤(1−ηµ)T−1∆ 1 +O ( 1√n )
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.