Transformers converge globally to the optimal DDPM denoiser for multi-token GMMs via self-attention mean denoising, with explicit token and iteration requirements.
Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Score-based generative models attain intrinsic Wasserstein-1 sample rates of order n to the power of -(beta+1)/(d+2beta) on d-dimensional smooth manifolds with beta-Holder densities.
For a broad class of coefficients, diffusion models achieve Õ(k/ε) iteration complexity for ε-accurate TV sampling under low-dimensional structure, independent of ambient dimension.
Diffusion models on manifold-supported data admit score decompositions whose statistical rates are controlled by intrinsic dimension and curvature.
citing papers explorer
-
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
Transformers converge globally to the optimal DDPM denoiser for multi-token GMMs via self-attention mean denoising, with explicit token and iteration requirements.
-
Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
Score-based generative models attain intrinsic Wasserstein-1 sample rates of order n to the power of -(beta+1)/(d+2beta) on d-dimensional smooth manifolds with beta-Holder densities.
-
Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
For a broad class of coefficients, diffusion models achieve Õ(k/ε) iteration complexity for ε-accurate TV sampling under low-dimensional structure, independent of ambient dimension.
-
Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
Diffusion models on manifold-supported data admit score decompositions whose statistical rates are controlled by intrinsic dimension and curvature.