Branching Stein Variational Gradient Descent for sampling multimodal distributions
Not on the map. Why?
Abstract (arXiv)
We propose a novel particle-based variational inference method designed to work with multimodal distributions. Our approach, referred to as Branched Stein Variational Gradient Descent (BSVGD), extends the classical Stein Variational Gradient Descent (SVGD) algorithm by incorporating a random branching mechanism that encourages the exploration of the state space. In this work, a theoretical guarantee for the convergence in distribution is presented, as well as numerical experiments to validate the suitability of our algorithm. Performance comparisons between the BSVGD and the SVGD are presented using the Wasserstein distance between samples and the corresponding computational times.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 31 references that are in the map. First posted on arXiv 16 Jun 2025.
Builds on
13 of 31 references.
References · 13
- 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
- 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
- 2017Stein Variational Gradient Descent as Gradient Flowcited by 152
- 2017Stein Variational Policy Gradientcited by 44
- 2020Stochastic Stein Discrepanciescited by 30
- 2018Learning Self-Imitating Diverse Policiescited by 29
- 2017Learning to Draw Samples with Amortized Stein Variational Gradient Descentcited by 28
- 2022A Finite-Particle Convergence Rate for Stein Variational Gradient Descentcited by 22
- 2018A Framework for Adaptive MCMC Targeting Multimodal Distributionscited by 21
- 2020Stein Variational Inference for Discrete Distributionscited by 16
- 2024Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descentcited by 14
- 2023Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descentcited by 13
Built on by
Not cited yet.