Research map / Optimization / Optimizers
Stein Variational Gradient Descent as Gradient Flow
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the continuous-time SVGD dynamics | SVGD · Target distribution approximation | KL divergence to the target | Helped |
| Use sufficiently small step sizes | Population SVGD · Target distribution approximation | KL divergence to the target | Helped |
Closest papers by meaning
- A Non-Asymptotic Analysis for Stein Variational Gradient Descent (NeurIPS 2020 · similarity 0.95)
- SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence (NeurIPS 2020 · similarity 0.94)
- Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent (NeurIPS 2023 · similarity 0.94)
- Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent (ICLR 2025 · similarity 0.92)
- Long-time asymptotics of noisy SVGD outside the population limit (ICLR 2025 · similarity 0.92)
- ELBOing Stein: Variational Bayes with Stein Mixture Inference (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.