Research map / Optimization / Optimizers
Stein Variational Gradient Descent as Moment Matching
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 linear features | SVGD · Multivariate Gaussian distributions | mean and covariance estimation: exactly estimates both the mean and the covariance matrix | Helped |
| Use random features of a strictly positive definite kernel | SVGD · Target distribution p | kernelized Stein discrepancy: \tilde O(1/\sqrt{n}) | Helped |
| Use linear features alone rather than a richer feature set | SVGD · Whole-distribution approximation | distributional consistency | Hurt |
| Use a Gaussian RBF kernel instead of linear features | SVGD · Gaussian targets | mean and variance estimation | Mixed |
Closest papers by meaning
- Stein Variational Gradient Descent With Matrix-Valued Kernels (NeurIPS 2019 · similarity 0.95)
- A Non-Asymptotic Analysis for Stein Variational Gradient Descent (NeurIPS 2020 · similarity 0.95)
- A Finite-Particle Convergence Rate for Stein Variational Gradient Descent (NeurIPS 2023 · similarity 0.94)
- ELBOing Stein: Variational Bayes with Stein Mixture Inference (ICLR 2025 · similarity 0.92)
- Long-time asymptotics of noisy SVGD outside the population limit (ICLR 2025 · similarity 0.91)
- Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent (ICLR 2025 · similarity 0.91)
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.