Skip to content

The critical slowing down in training diffusion models

May 2026 · 1 citation · 106 references
Physics Computer Science

TL;DR

It is demonstrated that diffusion models can overcome the critical slowing down through appropriate architectural design, and establish a controlled framework for understanding and improving learned sampling methods in statistical physics and beyond.

Abstract

Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently enabled major advances, their behavior remains poorly understood, with limited theoretical control over when and why they succeed. Here we provide such insight for diffusion models---a class of generative schemes highly effective in practice---by analyzing their application to the $O(n)$ model of statistical field theory in the Gaussian limit $n \to \infty$. In this analytically tractable setting, we show that training a score model with a one-layer network architecture matching the exact solution exhibits a form of critical slowing down in parameter learning. This slowing down also impacts the generation process, indicating that the well-known difficulties of sampling near criticality persist even for learned generative models. To overcome this bottleneck, we consider the power of architectural depth. We find that using a two-layer architecture drastically reduces the critical slowing down, with the training time scaling logarithmically rather than quadratically with system size. Using a Fourier implementation of the architecture, we further show that this acceleration in training time can be achieved without drastically increasing operational complexity. Taken together, these results demonstrate that diffusion models can overcome the critical slowing down through appropriate architectural design, and establish a controlled framework for understanding and improving learned sampling methods in statistical physics and beyond.

View source

Similar papers

Double Descent and Malign Overfitting in Diffusion Models

Overparameterization remains beneficial when paired with regularization: in the random-features theory and in U-Net experiments, optimally regularized large models---via a ridge penalty or early stopping, respectively---outperform any unregularized models.

Raphaël Urfin, Tony Bonnaire, Giulio Biroli et al. · 0 citations

First Learn, Then Memorize: The Spectral Bias of Diffusion Models

Analytically, the spectrum is solved in the lazy high-dimensional limit for both linear ($n \asymp d) and polynomial ($n \asymp d^k$) sample complexities, and it is proved through a bias--variance decomposition that the first bulk minimizes the approximation error while the second drives the error associated with memor...

Raphaël Urfin, Tony Bonnaire, Giulio Biroli et al. · 1 citation
#machine learning Preprint Oct 2026

Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis

Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we leverage Gaussian distributions to isolate this phenomenon. We establish 2-Wasserstein convergence bounds for optimized hyperparameters, showing that diffusion processes ach...

Adam Perbost, F. Bach, Pierre Marion · 0 citations
#machine learning Preprint Oct 2026

Data Free Training of Diffusion Models for Lattice Field Theories

Sampling equilibrium field configurations remains a major computational bottleneck in lattice field theory, motivating the development of generative samplers that can produce independent configurations. Diffusion models are promising for this purpose, but their standard denoising score matching objective requires sampl...

Dennis Grinwald, Ankur Singha, Khaled Kahouli et al. · 2 citations
Preprint Oct 2026

Composing and Steering Diffusion Models with Generalized Feynman-Kac Correctors

This work introduces the generalized Feynman-Kac correctors (GFKC), a principled framework for sampling from an arbitrary target function of several pretrained diffusion models and validates the method on analytic Gaussian models, where it closely matches the ground-truth targets.

Wael Mattar, Daniel Freedman · 0 citations

From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models

Experiments in controlled settings and on large-scale models show that $\sigma_c$ tracks memorization arising from duplication, overfitting, and outliers, and identifies both memorized and partially memorized examples in Stable Diffusion, which yields interpretable measures of the image spatial distribution and caption...

C. Amado, Marco Fumero, Francesco Locatello · 0 citations

Related blog posts

MIT News · Artificial Intelligence Sep 29, 2026

Who we become when we talk to machines

Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.