Conditional diffusion transformers and their latent variants receive score approximation and estimation rates, but the minimax optimality headline rests on setting a derived constant equal to 1/2.
Scalable diffusion models with transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
Conditional diffusion transformers and their latent variants receive score approximation and estimation rates, but the minimax optimality headline rests on setting a derived constant equal to 1/2.