mlsanityData to 14 Oct 2026

Long-time asymptotics of noisy SVGD outside the population limit

arXiv 2406.11929 ↗First posted 17 Jun 2024cs.LG math.PRcited by 3

Not on the map. Why?

Abstract (arXiv)

Stein Variational Gradient Descent (SVGD) is a widely used sampling algorithm that has been successfully applied in several areas of Machine Learning. SVGD operates by iteratively moving a set of interacting particles (which represent the samples) to approximate the target distribution. Despite recent studies on the complexity of SVGD and its variants, their long-time asymptotic behavior (i.e., after numerous iterations ) is still not understood in the finite number of particles regime. We study the long-time asymptotic behavior of a noisy variant of SVGD. First, we establish that the limit set of noisy SVGD for large is well-defined. We then characterize this limit set, showing that it approaches the target distribution as increases. In particular, noisy SVGD provably avoids the variance collapse observed for SVGD. Our approach involves demonstrating that the trajectories of noisy SVGD closely resemble those described by a McKean-Vlasov process.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

22 of 37 references.

References · 22

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  3. 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 227
  4. 2017Stein Variational Gradient Descent as Gradient Flowcited by 152
  5. 2023The probability flow ODE is provably fastcited by 146
  6. 2017Measuring Sample Quality with Kernelscited by 119
  7. 2020A Non-Asymptotic Analysis for Stein Variational Gradient Descentcited by 61
  8. 2017Message Passing Stein Variational Gradient Descentcited by 47
  9. 2017Stein Variational Policy Gradientcited by 44
  10. 2018Scaling limit of the Stein variational gradient descent: the mean field regimecited by 35
  11. 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 35
  12. 2021Annealed Stein Variational Gradient Descentcited by 26
10 more
  1. 2022A Finite-Particle Convergence Rate for Stein Variational Gradient Descentcited by 22
  2. 2021A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1cited by 21
  3. 2024S2AC: Energy-Based Reinforcement Learning with Stein Soft Actor Criticcited by 18
  4. 2022Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Conditioncited by 16
  5. 2021Stein Variational Gradient Descent: many-particle and long-time asymptoticscited by 15
  6. 2022Controlling Moments with Kernel Stein Discrepanciescited by 13
  7. 2023Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descentcited by 13
  8. 2019Scalable Thompson Sampling via Optimal Transportcited by 7
  9. 2023Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximationcited by 6
  10. 2017Learning Structural Weight Uncertainty for Sequential Decision-Makingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 2.

3 papers.

  1. 2024Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descentcited by 14
  2. 2026Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flowcited by 3
  3. 2026Quantitative Target Convergence and Uniform-in-Time Propagation of Chaos for Langevin-Regularized SVGDcited by 0