Penalized Nonreversible Langevin for Constrained Sampling

arXiv:2609.25381 · stat.ML, cs.LG, math.PR · Submitted 2026-09-21 · Read on arXiv

stat.ML, cs.LG, math.PR

Submitted: 2026-09-21

Updated: 2026-10-02

Comments: There are 68 pages and has 8 figures

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

Terminology

• Accuracy — 32× in this paper · explained in 1 episode
• Langevin Dynamics — 11× in this paper · explained in 2 episodes
• Wasserstein Distance — 3× in this paper · explained in 4 episodes
• Fisher Information — 2× in this paper · explained in 3 episodes
• Inverse Problem — 2× in this paper · explained in 2 episodes
• Approximation Bound — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Improved Analysis for Hessian-free High-resolution Monte Carlo Sampling
• Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms
• 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