mlsanityData to 14 Oct 2026

Diffusion at Absolute Zero: Langevin Sampling Using Successive Moreau Envelopes [conference paper]

arXiv 2502.01358 ↗First posted 3 Feb 2025math.OC cs.CV cs.NAcited by 6

Not on the map. Why?

Abstract (arXiv)

In this article we propose a novel method for sampling from Gibbs distributions of the form π(x)proptoexp(-U(x)) with a potential U(x). In particular, inspired by diffusion models we propose to consider a sequence (πtk)k of approximations of the target density, for which πtk≈ π for k small and, on the other hand, πtk exhibits favorable properties for sampling for k large. This sequence is obtained by replacing parts of the potential U by its Moreau envelopes. Sampling is performed in an Annealed Langevin type procedure, that is, sequentially sampling from πtk for decreasing k, effectively guiding the samples from a simple starting density to the more complex target. In addition to a theoretical analysis we show experimental results supporting the efficacy of the method in terms of increased convergence speed and applicability to multi-modal densities π.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

28 of 55 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2021Convex optimizationcited by 2,515
  5. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 208
  6. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 197
  7. 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 146
  8. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 130
  9. 2018Analysis of Langevin Monte Carlo via convex optimizationcited by 127
  10. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
  11. 2016Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreaucited by 84
  12. 2018Sharp convergence rates for Langevin dynamics in the nonconvex settingcited by 68
16 more
  1. 2020Total Deep Variation for Linear Inverse Problemscited by 53
  2. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Modelscited by 47
  3. 2013Proximal Markov chain Monte Carlo algorithmscited by 46
  4. 2019Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetrycited by 34
  5. 2022Stable Deep MRI Reconstruction using Generative Priorscited by 21
  6. 2022A Hamilton-Jacobi-based Proximal Operatorcited by 13
  7. 2019Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimizationcited by 12
  8. 2022Posterior-Variance-Based Error Quantification for Inverse Problems in Imagingcited by 12
  9. 2023Subgradient Langevin Methods for Sampling from Non-smooth Potentialscited by 11
  10. 2016Maximum-a-posteriori estimation with Bayesian confidence regionscited by 10
  11. 2020Belief Propagation Reloaded: Learning BP-Layers for Labeling Problemscited by 9
  12. 2022Computed Tomography Reconstruction using Generative Energy-Based Priorscited by 9
  13. 2022Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopescited by 7
  14. 2022Global Solutions to Nonconvex Problems by Evolution of Hamilton-Jacobi PDEscited by 6
  15. 2015Total variation on a treecited by 4
  16. 2024Ergodicity of Langevin Dynamics and its Discretizations for Non-smooth Potentialscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2025Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
  2. 2024The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
  3. 2026Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis
  4. 2025Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling
  5. 2024New algorithms for sampling and diffusion models
  6. 2024Diffusive Gibbs Sampling
  7. 2025Continuously Tempered Diffusion Samplers
  8. 2024A Practical Diffusion Path for Sampling