Stochastic Gradient Langevin Dynamics

Also known as SGLD

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 11

All topics

Penalized Nonreversible Langevin for Constrained Sampling
Sep 21, 2026Pervez Ali, Weihao Dong, Xiaoyu WangMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America · Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People’s Republic of China · FinTech Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People’s Republic of China
The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
Aug 6, 2026Iosif Lytras, Nikolaos Makras, Sotirios SabanisStochastic Gradient Langevin Dynamics Langevin Dynamics
School of Mathematics, University of Edinburgh, UK · National Technical University of Athens, Greece · Athena/Archimedes Research Centre, Greece
Comparing SGLD and a fixed-noise Predictor-Corrector adaptation in canonical Joint Energy-Based Models on CIFAR-10
Aug 5, 2026Dmytro KnopovStochastic Gradient Langevin Dynamics Langevin Dynamics
Faculty of Computer Sciences, Department of Mathematics, National University of Kyiv-Mohyla Academy, Kyiv, Ukraine.
RELTA-SGLD: Relative-Growth Localized Taming for Nonconvex Stochastic-Gradient Langevin Learning
Jul 21, 2026Yiwei Zhou, Ziheng ChenStochastic Gradient Langevin Dynamics Langevin Dynamics
School of Mathematics and Statistics, Yunnan University, Kunming, Yunnan 650500, China.
Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
Jun 27, 2026Bingye Ni, Xiaoyu Wang, Yingli Wang +1Markov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
FinTech Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People's Republic of China · School of Mathematical Science, Fudan University, Shanghai, People's Republic of China · Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America
Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic Gradient Noise and Localizing Taming
Jun 3, 2026Yiwei Zhou, Ziheng ChenStochastic Differential Equations Stochastic Gradient Langevin Dynamics
School of Mathematics and Statistics, Yunnan University, Kunming, Yunnan, 650500, China.
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
May 29, 2026Xiaoyu Wang, Jonathan H. HugginsMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Mathematics & Statistics, Boston University · Faculty of Computing & Data Sciences, Boston University
Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo
May 29, 2026Yu Wang, Jie Ding, Jonathan H. HugginsMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Mathematics & Statistics, Boston University · Questrom School of Business, Boston University · Faculty of Computing & Data Sciences, Boston University
Improved Guarantees for Langevin Monte Carlo with Average Smoothness
May 29, 2026Arnak S. Dalalyan, Avetik KaragulyanMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
CREST, ENSAE Paris, Institut Polytechnique de Paris and MBZUAI · L2S, CNRS, Centrale Supélec, Université Paris-Saclay
Decentralized Proximal Stochastic Gradient Langevin Dynamics
May 1, 2026Mohammad Rafiqul Islam, Lingjiong ZhuMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America
Quantum Speedups for Sampling and Non-convex Optimization with Stochastic Oracles
Apr 4, 2025Guneykan Ozgul, Xiantao Li, Mehrdad Mahdavi +1Markov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA · Department of Mathematics, Pennsylvania State University, University Park, PA, USA

Sep 21, 2026, stat.MLJ/K move · Enter open · S save

Penalized Nonreversible Langevin for Constrained Sampling

Pervez Ali, Weihao Dong, Xiaoyu Wang

Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America · Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People’s Republic of China · FinTech Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People’s Republic of China

Markov Chain Monte Carlo Stochastic Gradient Langevin Dynamics Langevin Dynamics

Open paper AskPDF arXiv

We propose penalized nonreversible Langevin algorithms for sampling from

π(x)\propto e^{-f(x)}\mathbf 1_{\mathcal C}(x)

, where

\mathcal C\subset\mathbb R^d

is a compact convex set. The algorithms combine a squared distance penalty with constant or compatible state dependent skew symmetric perturbations that preserve the penalized Gibbs distribution. For smooth, possibly nonconvex

f

, we derive nonasymptotic total variation bounds for the full gradient algorithm under a log Sobolev inequality. When unbiased stochastic gradients are available, we establish

2

-Wasserstein bounds under global contraction and Lipschitz conditions on the full drift in an adapted quadratic metric. For a fixed penalty parameter, the error relative to the penalized Gibbs distribution decays exponentially to an

\mathcal{O}(\sqrtη)

neighborhood, where

η

is the stepsize. We also bound the discrepancy between the penalized Gibbs distribution and the constrained target. In a two dimensional quadratic model, we establish nonreversible acceleration by tuning the skew perturbation to the curvature imbalance induced by penalization. With the target accuracy and smaller curvature fixed and initial Wasserstein distances uniformly bounded, tuning the skew perturbation improves the sufficient Euler iteration bound from linear to logarithmic in the curvature ratio. Numerical experiments evaluate the algorithms on constrained Bayesian regression, classification, neural networks, and truncated sampling, and examine the acceleration mechanism in a stochastic quadratic model.

Momentum

Related topics

Latest papers 11