AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions

Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu

JMLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 61 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MoLRG mixture of low-rank Gaussians parameterization instead of a single full-rank Gaussiantheoretical network parameterization · FashionMNISTdistance to U-Net samples: 72.62 -> 57.56Improved
use MoLRG mixture of low-rank Gaussians parameterization instead of a single full-rank Gaussiantheoretical network parameterization · MNISTdistance to U-Net samples: 69.12 -> 62.53Improved
use MoLRG mixture of low-rank Gaussians parameterization instead of a single full-rank Gaussiantheoretical network parameterization · CIFAR-10distance to U-Net samples: 33.55 -> 31.29Improved
use MoLRG mixture of low-rank Gaussians parameterization instead of a single full-rank Gaussiantheoretical network parameterization · FFHQdistance to U-Net samples: 36.75 -> 35.78Improved
normalize training sample count by intrinsic dimension N/ID instead of N/ID^2 as predictor of generalization (ablation)U-Net diffusion on MoLRG synthetic data · synthetic MoLRG (n=48, K=2)GL score fit to sigmoidImproved
normalize training sample count by intrinsic dimension N/ID instead of N/ID^2 as predictor of generalization (ablation)U-Net diffusion on real image datasets · CIFAR-10, CelebA, FFHQ, AFHQGL score collapse across datasetsImproved
increase number of training samples N past the intrinsic dimensiondiffusion models learning MoLRG · synthetic MoLRG phase transition (n=48, d 2-8, N 2-15)subspace recovery successImproved
steer along leading singular vectors of subspace basis instead of a random directionpretrained DDPM on MetFaces · image editingsemantic edit visibilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy