Stein Variational Gradient Descent

Also known as SVGD

Ask about this topic

Overview

Stein Variational Gradient Descent transports a set of particles toward a target distribution using its score, while kernel-based repulsion helps preserve diversity. It is used for Bayesian sampling and variational inference, as well as optimization, control, and learning tasks where distributions may be multimodal or constrained by geometry. Approaches include adaptive and multirate updates, manifold-aware kernels, Langevin regularization, and theoretical analyses of mean-field limits, finite-particle convergence, and propagation of chaos. A central challenge is obtaining reliable convergence and computational efficiency as dimension grows, especially when results depend strongly on kernel choice, target geometry, and the number of particles.

Latest papers

CardsList

18 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. Anchored Stein Variational Gradient Descent Algorithm for Non-smooth Sampling

    Oct 26, 2026Thanh Dang, Matthew X. Burns, Jiaming LiangStein Variational Gradient DescentSampling from Unnormalized Distributions

    Department of Computer Science, University of Rochester, Rochester, NY 14620. · Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY 14627 · Goergen Institute for Data Science and Artificial Intelligence and Department of Computer Science, University of Rochester, Rochester, NY 14620

  2. Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent

    Oct 13, 2026Chao Li, Mrinal K. Sen, Sergey Fomel +1Seismic ImagingBayesian Inverse Problems

    The University of Texas at Austin

  3. Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent

    Sep 8, 2026Quang-Duy Tran, Trung Le, Bao Duong +2Stiefel Manifold OptimizationUncertainty Quantification

    Deakin Applied Artificial Intelligence Initiative, Deakin University, Geelong, Australia · Department of Computer Science, Aalto University, Espoo, Finland · Department of Data Science & AI, Monash University, Melbourne, Australia

  4. Quantitative Target Convergence and Uniform-in-Time Propagation of Chaos for Langevin-Regularized SVGD

    Aug 28, 2026Sayan Banerjee, Dohyeon KimStein Variational Gradient DescentStochastic Differential Equations

    Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, 318 Hanes Hall, CB# 3260, Chapel Hill, NC 27599-3260, USA. · Department of Computing and Mathematical Sciences, California Institute of Technology, 1200 East California Boulevard, MC 305-16, Pasadena, CA 91125, USA.

  5. Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits

    Jul 16, 2026Trevor Teolis, Maarten V. de HoopKernel MethodsStein Variational Gradient Descent

    Rice University

  6. Reinforcement Learning for Flow-Matching Policies with Density Transport

    Jun 7, 2026Boshu Lei, Kostas Daniilidis, Antonio LoquercioFlow MatchingRobotic RL

    University of Pennsylvania · Philadelphia, PA 19103

  7. Variational Proximal Policy Optimization

    Jun 6, 2026Ousmane Amadou DiaRL for Language Model ReasoningProximal Policy Optimization

  8. Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials

    Jun 2, 2026Joanna Zou, Fraser Birks, Dallas Foster +1Machine Learning Interatomic PotentialsActive Learning

    Center for Computational Science & Engineering, Schwarzman College of Computing, MIT · Warwick Centre for Predictive Modelling, School of Engineering, University of Warwick · NVIDIA

  9. Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference

    May 26, 2026Jaewoo Lee, Hyeongyu Kang, Dohyun Kim +9Stein Variational Gradient Descent

    1KAIST · 2MongooseAI · 3Mila – Quebec AI Institute +3

  10. Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flow

    May 10, 2026Lénaïc Chizat, Maria Colombo, Roberto Colombo +1Dynamical SystemsOptimization Convergence Analysis

  11. From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing

    Apr 20, 2026Linfeng Liang, Xiao Cheng, Tsong Yueh Chen +1Autonomous Driving Safety EvaluationAutonomous Driving Simulation

    Macquarie University, Australia · Swinburne University of Technology, Australia

  12. Stein Variational Black-Box Combinatorial Optimization

    Apr 17, 2026Thomas Landais, Olivier Goudet, Adrien Goëffon +2Stochastic OptimizationBlack-Box Optimization

    LERIA, Université d’Angers, 2 Boulevard Lavoisier, Angers 49045, France

  13. Multirate Stein Variational Gradient Descent for Efficient Bayesian Sampling

    Apr 5, 2026Arash SarsharStein Variational Gradient DescentBayesian Inference

    Department of Computer Engineering and Computer Science, California State University, Long Beach, 90840, CA, USA

  14. Stein Variational Ergodic Surface Coverage with SE(3) Constraints

    Mar 10, 2026Jiayun Li, Yufeng Jin, Sangli Teng +2Safe Robot ManipulationTrajectory Optimization

    Department of Computer Science, TU Darmstadt, Darmstadt, Germany. · Hessian.AI, Darmstadt, Germany. · Honda Research Institute Europe GmbH, Offenbach, Germany. +1

  15. Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation

    Mar 9, 2026Adam Rozzio, Rafael Athanasiades, O. Deniz AkyildizMaximum Marginal Likelihood EstimationExpectation-Maximization

    Department of Mathematics, Ecole Normale Supérieure Paris-Saclay, France · Department of Mathematics, Imperial College London, UK

  16. Probabilistic Inference and Learning with Stein's Method

    Mar 8, 2026Qiang Liu, Lester Mackey, Chris OatesStein Variational Gradient Descent

    University of Texas at Austin · Microsoft Research · Newcastle University +1

  17. Stein-based Optimization of Sampling Distributions in Model Predictive Path Integral Control

    Nov 3, 2025Jace Aldrich, Odest Chadwicke JenkinsRobotic ControlStochastic Optimal Control

    Laboratory for Perceptive RObotics and Grounded REasoning SystemS and Robotics Department at the University of Michigan, Ann Arbor, USA

  18. Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

    Sep 13, 2024Sayan Banerjee, Krishnakumar Balasubramanian, Promit GhosalKernel MethodsVariational Inference

    Department of Statistics and Operations Research, University of North Carolina, Chapel Hill. · Department of Statistics, University of California, Davis. · Department of Statistics, University of Chicago.