Langevin Dynamics

Follow this topic Ask about this topic

Recent momentum

-33%

4 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Langevin Dynamics.

51 papers

Latest in Langevin Dynamics

Open your feed →

Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows
Sep 16, 2026Francesca Romana Crucinio, Sahani PathirajaWasserstein Gradient Flows Non-Log-Concave
Online local learning for generative thermodynamic computing
Sep 14, 2026Huilin Wang, Weibing DengThermodynamics Langevin Dynamics
Poisson-Corrector Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
Sep 14, 2026Yuchen Xin, Zhihua ZhangLangevin Dynamics Lipschitz Constant
The Depth Flow of Token Representations Is Nonlinear and Does Not Descend Its Own Density
Aug 30, 2026Alexandre QuemyResidual Stream Langevin Dynamics
Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
Aug 13, 2026Yuchen Xin, Zhihua ZhangLangevin Dynamics Lipschitz Constant
The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
Aug 6, 2026Iosif Lytras, Nikolaos Makras, Sotirios SabanisLangevin Dynamics Finite Time Analysis
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Aug 6, 2026Yingqing Guo, Hui Yuan, Zijian He +2Flow-Based Policy Reward Gradients
Particle-based Generalised Stochastic Optimisation
Aug 3, 2026Jiechen Jackie Zhang, O. Deniz AkyildizStochastic Optimization Langevin Dynamics
Wasserstein mixing time of the unadjusted Langevin algorithm
Aug 3, 2026Francesco Pedrotti, Peter A. WhalleyLangevin Dynamics Wasserstein Distance
Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy
Jul 27, 2026Sayantari Ghosh, Saumik Bhattacharya, Partha Pratim ChakrabartiComplex Networks Conformity
A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing
Jul 17, 2026Owen Lockwood, Jérémy Béjanin, Joost Bus +4Thermodynamics In-Memory Computing
Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
Jul 16, 2026Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed +1Hamiltonian Monte Carlo Langevin Dynamics
Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits
Jul 16, 2026Trevor Teolis, Maarten V. de HoopLangevin Dynamics Invariance
Moment-Resolved Readout and Reservoir Diversity in Nonequilibrium Langevin Computing
Jul 16, 2026JiZheng Duan, MingYang Zhao, YanWei Chen +1Reservoir Computing Readout
Avoiding unsafe sets when training with Langevin Dynamics
Jul 8, 2026Adam M. ObermanLoss Landscape Langevin Dynamics
Tightening the Score Matching Gap for Diffusion Models
Jul 5, 2026Benjamin Dupuis, Tyler Farghly, Maxime Haddouche +2Score-Based Diffusion Model Kullback-Leibler Divergence
Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
Jun 27, 2026Bingye Ni, Xiaoyu Wang, Yingli Wang +1Langevin Dynamics Variance Reduction
Accelerated sampling using SamAdams variable timesteps and position-adaptive Langevin dynamics
Jun 25, 2026Benedict Leimkuhler, Peter A. WhalleyLangevin Dynamics Classical Numerical Solver
Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic Gradient Noise and Localizing Taming
Jun 3, 2026Yiwei Zhou, Ziheng ChenStochastic Gradient Descent Langevin Dynamics
Speculative Sampling For Faster Molecular Dynamics
Jun 1, 2026Arthur Kosmala, Stephan Günnemann, Meng Gao +1Molecular Dynamics Langevin Dynamics
Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
Jun 1, 2026Xiang Li, Dianbo Liu, Kenji KawaguchiGenerative Priors Generative Models
Improved Guarantees for Langevin Monte Carlo with Average Smoothness
May 29, 2026Arnak S. Dalalyan, Avetik KaragulyanLangevin Dynamics Non-Log-Concave
Thinned Mean Field Langevin Dynamics
May 27, 2026Zonghao Chen, Heishiro Kanagawa, François-Xavier Briol +2Mean-Field Limit Langevin Dynamics
Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning
May 25, 2026Zhaoyu Zhu, Rui Gao, Shuang LiPolicy Gradient Entropy-Regularized Equilibrium Selection
On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy
May 22, 2026Aratrika Mustafi, Soumya MukherjeeDifferential Privacy Wasserstein Gradient Flows
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
May 21, 2026Igor Ignashin, Anna Radovskaya, Andrew Semenov +7Stochastic Gradient Descent Stochastic Differential Equations
Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference
May 20, 2026Camille Touron, Gabriel V. Cardoso, Julyan Arbel +1Langevin Dynamics Biasing Score Estimation
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
May 18, 2026Benjamin Sterling, Mónica F. Bugallo, Tom TirerLangevin Dynamics Memorization
Geometric Dictionary Learning of Dynamical Systems with Optimal Transport
May 18, 2026Thibaut Germain, Sami Chemlal, Rémi Flamary +2Dynamical Systems Learning Dynamics
StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
May 15, 2026Gurjeet Jagwani, Stephen Thorp, Sinan Deger +1Likelihood Normalizing Flows
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
May 15, 2026Lorenzo Baldassari, Josselin Garnier, Knut Solna +1Langevin Dynamics Diffusion Sampling
Complexity of Non-Log-Concave Sampling in Fisher Information
May 15, 2026Sinho Chewi, Andre WibisonoNon-Log-Concave Optimal Sample Complexity
Training-Free Generative Sampling via Moment-Matched Score Smoothing
May 14, 2026Zhenyu Yao, Daniel PaulinScore-Based Diffusion Model Langevin Dynamics
Gradient-Free Noise Optimization for Reward Alignment in Generative Models
May 12, 2026Jeongsol Kim, Hongeun Kim, Jian Wang +1Reward Gradients Gradient-Based Optimization
Metropolis-Adjusted Diffusion Models
May 10, 2026Kevin H. Lam, Tyler Farghly, Christopher Williams +3Score-Based Diffusion Model Langevin Dynamics
Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
May 8, 2026Atsushi Nitanda, Dake Bu, Yueming Lyu +1Langevin Dynamics Latent Trajectories
Conservative Flows: A New Paradigm of Generative Models
May 7, 2026Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof +1Generative Flow Networks Generative Models
Time-Inhomogeneous Preconditioned Langevin Dynamics
May 7, 2026Alexander Falk, Laurenz Nagler, Andreas Habring +1Langevin Dynamics Spectral Preconditioning
Energy Generative Modeling: A Lyapunov-based Energy Matching Perspective
May 7, 2026Yixuan Wang, Wenqian Xue, Warren E. DixonLangevin Dynamics Generative Models
Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees
May 6, 2026Ahmad Aghapour, Erhan Bayraktar, Asaf CohenIll-Posed Inverse Problem Langevin Dynamics
Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision
May 1, 2026Jiali Cui, Zhiqiang Lao, Heather YuVariational Autoencoder Markov Chain Monte Carlo
Conditional Score-Based Modeling of Effective Langevin Dynamics
Apr 27, 2026Ludovico T. GiorginiLangevin Dynamics Reduced-Order Models
Symmetric Equilibrium Propagation for Thermodynamic Diffusion Training
Apr 26, 2026Aditi DeScore-Based Diffusion Model Langevin Dynamics
Geometric regularization of autoencoders via observed stochastic dynamics
Apr 17, 2026Sean Hill, Felix X. -F. YeStochastic Dynamics Latent Cluster Geometry
Local exponential stability of mean-field Langevin descent-ascent and associated particle system
Feb 2, 2026Geuntaek Seo, Minseop Shin, Pierre Monmarché +1Mean-Field Limit Nash Equilibrium
Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
Oct 14, 2025Joanna Marks, Tim Y. J. Wang, O. Deniz AkyildizLangevin Dynamics Maximum Likelihood
Neural Langevin Machine: a local asymmetric learning rule can be creative
Jun 30, 2025Zhendong Yu, Weizhong Huang, Haiping HuangLangevin Dynamics Generative Models
Gaussian Invariant Markov Chain Monte Carlo
Jun 26, 2025Michalis K. Titsias, Angelos Alexopoulos, Siran Liu +1Markov Chain Monte Carlo Langevin Dynamics
Continuous Policy and Value Iteration for Stochastic Control Problems and Its Convergence
Jun 9, 2025Qi Feng, Gu WangStochastic Optimal Control Value Functions
Generalization Bounds for Markov Algorithms through Entropy Flow Computations
Feb 11, 2025Benjamin Dupuis, Maxime Haddouche, George Deligiannidis +1Generalization Bounds Entropy-Regularized Equilibrium Selection
Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
Date pendingSaumya Goyal, Rohith Rongali, Ritabrata Ray +1Gradient Descent Hyperparameter Optimization

Sep 16, 2026 · stat.MLJ/K move · Enter open · S save

Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows

Francesca Romana Crucinio, Sahani Pathiraja

We study the convergence of Wasserstein-Fisher-Rao (WFR) gradient flows for sampling from probability distributions known up to a normalisation constant. By combining Wasserstein transport with Fisher-Rao birth-death dynamics, WFR flows balance exploration and selection. These flows have been recognised as a promising mechanism to accelerate convergence beyond Langevin dynamics. We show that for a class of strongly log-concave target distributions satisfying additional curvature conditions, WFR flows preserve strong log-concavity, in contrast to Wasserstein flows which enjoy this property only in the Gaussian setting. Exploiting this result, we derive explicit non-asymptotic convergence rates for the symmetrised Kullback-Leibler divergence, without requiring a warm-start as required in current estimates. In particular, we show that the convergence rate decomposes additively into Wasserstein and Fisher-Rao contributions, thereby confirming a recent conjecture within this setting. These results provide refined convergence guarantees and further develop the theoretical foundations of WFR gradient flows for sampling and Bayesian inference.

Wasserstein Gradient Flows Non-Log-Concave Langevin Dynamics Gradient Flow Convergence

Open paper Ask about it PDF