Diffusion annealed Langevin dynamics: a theoretical study

• URL: http://arxiv.org/abs/2511.10406v1
• Date: Fri, 14 Nov 2025 01:49:29 GMT
• Title: Diffusion annealed Langevin dynamics: a theoretical study
• Authors: Patrick Cattiaux, Paula Cordero-Encinar, Arnaud Guillin,
• Abstract summary: We study a score-based diffusion process recently introduced in the theory of generative models.<n>We show that strengthening the Poincaré inequality into a logarithmic Sobolev inequality improves the efficiency of the model.
• Score: 1.0514231683620514
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this work we study the diffusion annealed Langevin dynamics, a score-based diffusion process recently introduced in the theory of generative models and which is an alternative to the classical overdamped Langevin diffusion. Our goal is to provide a rigorous construction and to study the theoretical efficiency of these models for general base distribution as well as target distribution. As a matter of fact these diffusion processes are a particular case of Nelson processes i.e. diffusion processes with a given flow of time marginals. Providing existence and uniqueness of the solution to the annealed Langevin diffusion leads to proving a Poincaré inequality for the conditional distribution of $X$ knowing $X+Z=y$ uniformly in $y$, as recently observed by one of us and her coauthors. Part of this work is thus devoted to the study of such Poincaré inequalities. Additionally we show that strengthening the Poincaré inequality into a logarithmic Sobolev inequality improves the efficiency of the model.

Related papers

• A Unification of Discrete, Gaussian, and Simplicial Diffusion [32.86558714543654]
  We show that Wright-Fisher simplicial diffusion is more stable and outperforms previous simplicial diffusion models on conditional DNA generation.<n>We also show that we can train models on multiple domains at once that are competitive with models trained on any individual domain.
  arXiv  Detail & Related papers  (2025-12-17T19:39:33Z)
• Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models [50.77646970127369]
  We propose an energy-based diffusion model with a Fokker--Planck-derived regularization term to enforce consistency.<n>We demonstrate our approach by sampling and simulating multiple biomolecular systems, including fast-folding proteins.
  arXiv  Detail & Related papers  (2025-06-20T16:38:29Z)
• Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling [1.9526430269580959]
  We provide non-asymptotic error bounds for the Langevin dynamics where the path of distributions is defined as Gaussian convolutions of the data distribution as in diffusion models.<n>We then extend our results to recently proposed heavy-tailed (Student's t) diffusion paths, demonstrating their theoretical properties for heavy-tailed data distributions for the first time.
  arXiv  Detail & Related papers  (2025-02-13T13:18:30Z)
• Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory [87.00653989457834]
  Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. Despite the empirical success, theory of conditional diffusion models is largely missing. This paper bridges the gap by presenting a sharp statistical theory of distribution estimation using conditional diffusion models.
  arXiv  Detail & Related papers  (2024-03-18T17:08:24Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [49.97755400231656]
  We show that a new accelerated DDPM sampler achieves accelerated performance for three broad distribution classes not considered before.<n>Our results show an improved dependency on the data dimension $d$ among accelerated DDPM type samplers.
  arXiv  Detail & Related papers  (2024-02-21T16:11:47Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• Lipschitz Singularities in Diffusion Models [64.28196620345808]
  Diffusion models often display the infinite Lipschitz property of the network with respect to time variable near the zero point.<n>We propose a novel approach, dubbed E-TSDM, which alleviates the Lipschitz singularities of the diffusion model near the zero point.<n>Our work may advance the understanding of the general diffusion process, and also provide insights for the design of diffusion models.
  arXiv  Detail & Related papers  (2023-06-20T03:05:28Z)
• Diffusion Models are Minimax Optimal Distribution Estimators [49.47503258639454]
  We provide the first rigorous analysis on approximation and generalization abilities of diffusion modeling. We show that when the true density function belongs to the Besov space and the empirical score matching loss is properly minimized, the generated data distribution achieves the nearly minimax optimal estimation rates.
  arXiv  Detail & Related papers  (2023-03-03T11:31:55Z)
• Convergence of denoising diffusion models under the manifold hypothesis [3.096615629099617]
  Denoising diffusion models are a recent class of generative models exhibiting state-of-the-art performance in image and audio synthesis. This paper provides the first convergence results for diffusion models in a more general setting.
  arXiv  Detail & Related papers  (2022-08-10T12:50:47Z)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)
• Exponential ergodicity of mirror-Langevin diffusions [16.012656579770827]
  We propose a class of diffusions called Newton-Langevin diffusions and prove that they converge to stationarity exponentially fast. We give an application to the problem of sampling from the uniform distribution on a convex body using a strategy inspired by interior-point methods.
  arXiv  Detail & Related papers  (2020-05-19T18:00:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.