SiLD is a score-matching framework that learns both manifold projection and intrinsic density from a single objective, with proven sample complexity depending only on intrinsic dimension.
Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality.Mathematics of Operations Research, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Causality-encoded diffusion models use a known DAG to train graph-consistent conditional diffusions for observational recovery, interventional sampling via fixed-variable propagation, and a resampling-based directed edge test with convergence rates depending on local dimension.
citing papers explorer
-
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
SiLD is a score-matching framework that learns both manifold projection and intrinsic density from a single objective, with proven sample complexity depending only on intrinsic dimension.
-
Causality-Encoded Diffusion Models for Interventional Sampling and Edge Inference
Causality-encoded diffusion models use a known DAG to train graph-consistent conditional diffusions for observational recovery, interventional sampling via fixed-variable propagation, and a resampling-based directed edge test with convergence rates depending on local dimension.