Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms

arXiv:2606.28808 · stat.ML, cs.LG, math.PR · Submitted 2026-06-27 · Read on arXiv

Bingye Ni, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu

stat.ML, cs.LG, math.PR

Submitted: 2026-06-27

Comments: 49 pages, 12 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Langevin Dynamics — 44× in this paper · explained in 2 episodes
• Convergence Guarantees — 6× in this paper · explained in 3 episodes
• Antisymmetric Coupling — 2× in this paper · explained in 1 episode
• Inverse Problem — 2× in this paper · explained in 2 episodes
• Ornstein–Uhlenbeck Process — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Wasserstein Distance — 2× in this paper · explained in 4 episodes
• 2-Wasserstein Distance — 1× in this paper · explained in 1 episode
• Active Learning — 1× in this paper · explained in 6 episodes
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Hilbert Space — 1× in this paper · explained in 2 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes

Sources

• DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
• Non-Reversible Langevin Algorithms for Constrained Sampling
• Nonreversible Langevin Samplers: Splitting Schemes, Analysis and Implementation
• Generalized EXTRA stochastic gradient Langevin dynamics
• Bayesian Active Learning for Classification and Preference Learning
• Non-Convex Optimization via Non-Reversible Stochastic Gradient Langevin Dynamics
• Regime-Switching Langevin Monte Carlo Algorithms
• Sampling non-log-concave densities via Hessian-free high-resolution dynamics

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier