arXiv Machine Learning June 5, 2026 By Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan

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

Read the original on arXiv Machine Learning →

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.

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

diffusion

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

arXiv Machine Learning

Jul 20

Diffusion models recover accurate mixture weights despite score function insensitivity

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.

By Andrew Dennehy, Ramchandran Muthukumar, Rebecca Willett, Nisha Chandramoorthy

diffusion multimodal benchmarks

arXiv Machine Learning

Jun 5

On the Robustness of Langevin Dynamics to Score Function Error

arXiv:2603. 11319v2 Announce Type: replace Abstract: We consider the robustness of score-based generative modeling to errors in the estimate of the score function.

By Daniel Yiming Cao, August Y. Chen, Karthik Sridharan, Yuchen Wu

diffusion

arXiv Machine Learning

Jul 10

Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling

arXiv:2607. 08757v1 Announce Type: cross Abstract: Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory.

By Yiwei Zhou

diffusion

arXiv AI

Aug 5

A Hyperfinite Framework for Score-Based Generative Modeling

arXiv:2608. 02799v1 Announce Type: cross Abstract: Score-based diffusion models are typically formulated using continuous-time stochastic differential equations and measure-theoretic stochastic calculus.

By Sunder Ram Krishnan

diffusion

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

Related stories

Tightening the Score Matching Gap for Diffusion Models

Diffusion models recover accurate mixture weights despite score function insensitivity

On the Robustness of Langevin Dynamics to Score Function Error

Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling

A Hyperfinite Framework for Score-Based Generative Modeling

Heteroscedasticity of Denoising Score Matching with Generalised Smooth Noise