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.
When scores learn geometry: Rate separations under the manifold hypothesis
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Discrete diffusion models learn data support before frequencies because the exact reverse process decomposes edits into a dominant validity scale and a finer probability coefficient.
Diffusion models on manifold-supported data admit score decompositions whose statistical rates are controlled by intrinsic dimension and curvature.
x-prediction maintains manifold adherence during training-free diffusion guidance better than ε- or v-prediction, per theoretical analysis and experiments on bird classification and style transfer.
Diffusion models require new generalization frameworks because memorization and novel generation are incompatible, so research should focus on what models learn before memorization begins.
citing papers explorer
-
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.
-
Support Before Frequency in Discrete Diffusion
Discrete diffusion models learn data support before frequencies because the exact reverse process decomposes edits into a dominant validity scale and a finer probability coefficient.
-
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.
-
Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold
x-prediction maintains manifold adherence during training-free diffusion guidance better than ε- or v-prediction, per theoretical analysis and experiments on bird classification and style transfer.
-
Understanding diffusion models requires rethinking (again) generalization
Diffusion models require new generalization frameworks because memorization and novel generation are incompatible, so research should focus on what models learn before memorization begins.