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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. 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 Machine Learning

Aug 21

Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation

arXiv:2605. 22950v2 Announce Type: replace-cross Abstract: Score matching is an alternative to maximum likelihood estimation when the normalizing constant is unknown or too costly to evaluate.

By Benedikt L\"utke Schwienhorst, Nadja Klein, Johannes Lederer

diffusion multimodal

arXiv Machine Learning

Sep 10

DDPM Score Matching and Distribution Learning

arXiv:2504.05161v2 Announce Type: replace-cross Abstract: Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key...

By Sinho Chewi, Alkis Kalavasis, Anay Mehrotra, Omar Montasser

diffusion multimodal

arXiv Machine Learning

Sep 10

Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression

arXiv:2609.05688v1 Announce Type: new Abstract: We study variance-preserving diffusion of the response in mixed linear regression (MLR) with unknown mixing weights. Our analysis separates the statist...

By Zhankun Luo, Abolfazl Hashemi

diffusion

One email a morning, machine-written

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

Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation

DDPM Score Matching and Distribution Learning

Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression