arXiv Machine Learning June 10, 2026 By Peng Wang, Huijie Zhang, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu

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

Read the original on arXiv Machine Learning →

arXiv:2409. 02426v5 Announce Type: replace Abstract: Despite their empirical success across a wide range of generative tasks, the fundamental principles underlying the ability of diffusion models to learn data distributions are poorly understood.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

diffusion

arXiv Machine Learning

Aug 10

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

arXiv:2409. 18804v3 Announce Type: replace-cross Abstract: Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond.

By Iskander Azangulov, George Deligiannidis, Judith Rousseau

diffusion benchmarks

arXiv Machine Learning

Jun 19

Score Approximation for Diffusion Models on Arbitrary Low-Dimensional Structures

arXiv:2606. 19894v1 Announce Type: new Abstract: The remarkable success of score-based diffusion models has spurred significant efforts to establish their theoretical foundations.

By Xinhe Mu, Zaijiu Shang, Zhaoqi Zhou, Chuan Zhou, Qi Meng, Guiying Yan, Zhiming Ma

diffusion

arXiv Machine Learning

Aug 6

Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds

arXiv:2608. 04827v1 Announce Type: cross Abstract: We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds.

By Yizhu Wang, Mu Niu, Xiaochen Yang

diffusion benchmarks

arXiv Machine Learning

Jun 15

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

arXiv:2606. 13796v1 Announce Type: cross Abstract: Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution.

By Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan

diffusion

arXiv AI

Jul 7

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

arXiv:2602. 02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed.

By Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan

diffusion

arXiv Machine Learning

Jun 11

A theory of learning data statistics in diffusion models, from easy to hard

arXiv:2603. 12901v2 Announce Type: replace-cross Abstract: While diffusion models have emerged as a powerful class of generative models, their learning dynamics remain poorly understood.

By Lorenzo Bardone, Claudia Merger, Sebastian Goldt

diffusion safety

Related stories

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

Score Approximation for Diffusion Models on Arbitrary Low-Dimensional Structures

Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

A theory of learning data statistics in diffusion models, from easy to hard