Diffusion at Absolute Zero: Langevin Sampling Using Successive Moreau Envelopes [conference paper]
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
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2021Convex optimizationcited by 2,515
- 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 208
- 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 197
- 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 146
- 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 130
- 2018Analysis of Langevin Monte Carlo via convex optimizationcited by 127
- 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
- 2016Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreaucited by 84
- 2018Sharp convergence rates for Langevin dynamics in the nonconvex settingcited by 68
16 more
- 2020Total Deep Variation for Linear Inverse Problemscited by 53
- 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Modelscited by 47
- 2013Proximal Markov chain Monte Carlo algorithmscited by 46
- 2019Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetrycited by 34
- 2022Stable Deep MRI Reconstruction using Generative Priorscited by 21
- 2022A Hamilton-Jacobi-based Proximal Operatorcited by 13
- 2019Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimizationcited by 12
- 2022Posterior-Variance-Based Error Quantification for Inverse Problems in Imagingcited by 12
- 2023Subgradient Langevin Methods for Sampling from Non-smooth Potentialscited by 11
- 2016Maximum-a-posteriori estimation with Bayesian confidence regionscited by 10
- 2020Belief Propagation Reloaded: Learning BP-Layers for Labeling Problemscited by 9
- 2022Computed Tomography Reconstruction using Generative Energy-Based Priorscited by 9
- 2022Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopescited by 7
- 2022Global Solutions to Nonconvex Problems by Evolution of Hamilton-Jacobi PDEscited by 6
- 2015Total variation on a treecited by 4
- 2024Ergodicity of Langevin Dynamics and its Discretizations for Non-smooth Potentialscited by 3
Built on by
Citing papers per year: 2025: 2; 2026: 4.
6 papers.
- 2025Learning Regularization Functionals for Inverse Problems: A Comparative Studycited by 15
- 2026DC-LA: Difference-of-Convex Langevin Algorithmcited by 2
- 2026Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Samplingcited by 2
- 2025Preconditioned Regularized Wasserstein Proximal Samplingcited by 1
- 2026Time-Inhomogeneous Preconditioned Langevin Dynamicscited by 0
- 2026R'enyi Tracking Bounds for Langevin Dynamics with Moving Targetscited by 0
- 2026R'enyi Tracking Bounds for Langevin Dynamics with Moving Targets25 Aug 2026
- 2026Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling13 Aug 2026
- 2026Time-Inhomogeneous Preconditioned Langevin Dynamics7 May 2026
- 2026DC-LA: Difference-of-Convex Langevin Algorithm30 Jan 2026
- 2025Learning Regularization Functionals for Inverse Problems: A Comparative Study2 Oct 2025
- 2025Preconditioned Regularized Wasserstein Proximal Sampling1 Sep 2025
Similar, not cited
Close in wording, no citation either way
- 2025Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
- 2024The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
- 2026Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis
- 2025Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling
- 2024New algorithms for sampling and diffusion models
- 2024Diffusive Gibbs Sampling
- 2025Continuously Tempered Diffusion Samplers
- 2024A Practical Diffusion Path for Sampling