arXiv Machine Learning July 20, 2026 By Andrew Dennehy, Ramchandran Muthukumar, Rebecca Willett, Nisha Chandramoorthy

Diffusion models recover accurate mixture weights despite score function insensitivity

Read the original on arXiv Machine Learning →

arXiv:2607. 15485v1 Announce Type: new Abstract: Score-based generative models exhibit a puzzling behavior: they often appear to cover all modes of a target multimodal distribution and yet may fail to learn the correct relative mode amplitudes, which can be interpreted as mixture weights.

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

arXiv Machine Learning

Aug 5

Heteroscedasticity of Denoising Score Matching with Generalised Smooth Noise

arXiv:2508. 01597v2 Announce Type: replace Abstract: Score Matching (SM) is a powerful framework for estimating the log-density derivatives of a distribution without calculating its normalizing constants.

By Juyan Zhang, Rhys Newbury, Xinyang Zhang, Tin Tran, Dana Kulic, Michael Burke

diffusion

arXiv Machine Learning

Jun 5

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors

arXiv:2606. 06179v1 Announce Type: cross Abstract: Score-based diffusion models are typically trained by minimizing the $L^2$ score matching error, and standard theoretical analyses rely on this quantity to bound the sampling discrepancy between the learned and target distributions.

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

diffusion

arXiv Machine Learning

Jul 28

From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models

arXiv:2607. 23226v1 Announce Type: new Abstract: Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped.

By Jinshu Huang, Yiming Jiang, Chunlin Wu

diffusion

arXiv AI

Jun 29

Class-frequency Guided Noise Schedule for Diffusion Models

arXiv:2606. 27696v1 Announce Type: cross Abstract: In this paper, we are the first to examine the correlations between class frequency and the multi-scale noise schedule within diffusion models.

By Jiequan Cui, Beier Zhu, Qingshan Xu, Xiaojuan Qi, Bei Yu, Hanwang Zhang

diffusion computer-vision

arXiv Machine Learning

Jul 14

Low-dimensional adaptation of diffusion models: Convergence in total variation

arXiv:2501. 12982v3 Announce Type: replace-cross Abstract: This paper investigates how diffusion generative models leverage (unknown) low-dimensional structure to accelerate sampling.

By Jiadong Liang, Zhihan Huang, Yuxin Chen

diffusion benchmarks

arXiv Machine Learning

Jul 7

Tightening the Score Matching Gap for Diffusion Models

arXiv:2607. 04442v1 Announce Type: cross Abstract: Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution.

By Benjamin Dupuis, Tyler Farghly, Maxime Haddouche, Alain Durmus, Umut Simsekli

diffusion benchmarks

Related stories

Heteroscedasticity of Denoising Score Matching with Generalised Smooth Noise

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors

From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models

Class-frequency Guided Noise Schedule for Diffusion Models

Low-dimensional adaptation of diffusion models: Convergence in total variation

Tightening the Score Matching Gap for Diffusion Models