mlsanityData to 7 Oct 2026

A Note on the Convergence of Mirrored Stein Variational Gradient Descent under (L0,L1)-Smoothness Condition

arXiv 2206.09709 ↗First posted 20 Jun 2022math.OC cs.LG math.STcited by 4

Not on the map. Why?

Abstract (arXiv)

In this note, we establish a descent lemma for the population limit Mirrored Stein Variational Gradient Method~(MSVGD). This descent lemma does not rely on the path information of MSVGD but rather on a simple assumption for the mirrored distribution nablaPsi#πproptoexp(-V). Our analysis demonstrates that MSVGD can be applied to a broader class of constrained sampling problems with non-smooth V. We also investigate the complexity of the population limit MSVGD in terms of dimension d.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

16 of 26 references.

References · 16

  1. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  2. 2019Why gradient clipping accelerates training: A theoretical justification for adaptivitycited by 335
  3. 2017Stein Variational Gradient Descent as Gradient Flowcited by 149
  4. 2017Measuring Sample Quality with Kernelscited by 119
  5. 2019On the geometry of Stein variational gradient descentcited by 82
  6. 2018Mirrored Langevin Dynamicscited by 61
  7. 2020A Non-Asymptotic Analysis for Stein Variational Gradient Descentcited by 61
  8. 2020Wasserstein Control of Mirror Langevin Monte Carlocited by 55
  9. 2020Efficient constrained sampling via the mirror-Langevin algorithmcited by 55
  10. 2018A Stein variational Newton methodcited by 49
  11. 2018Scaling limit of the Stein variational gradient descent: the mean field regimecited by 35
  12. 2019Stein Variational Gradient Descent With Matrix-Valued Kernelscited by 32
4 more
  1. 2020Stochastic Stein Discrepanciescited by 30
  2. 2021Sampling with Mirrored Stein Operatorscited by 17
  3. 2022Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Conditioncited by 16
  4. 2019A stochastic version of Stein Variational Gradient Descent for efficient samplingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2023Towards a Better Theoretical Understanding of Independent Subnetwork Trainingcited by 6
  2. 2023Rethinking SIGN Training: Provable Nonconvex Acceleration without First- and Second-Order Gradient Lipschitzcited by 4
  3. 2023Learning Rate Free Sampling in Constrained Domainscited by 3
  4. 2026Quantitative Local Convergence of Mean-Field Stein Variational Gradient Flowcited by 1