Research map / Optimization / Optimizers
A Convergence Theory for SVGD in the Population Limit under Talagrand’s Inequality T1
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 |
|---|---|---|---|
| Analyze population-limit SVGD as gradient descent over probability measures, assuming T1 rather than a uniformly bounded KSD trajectory | SVGD · Non-logconcave targets satisfying T1; population limit | iterations for squared KSD accuracy ε: \tilde{\Omega}\left(\frac{L{d}^{3/2}}{\lambda^{1/2}\varepsilon}\right) | Helped |
| Use a fixed step size satisfying the stated bounds, without requiring a uniform KSD bound along the trajectory | Population-limit SVGD · Targets satisfying T1 and the paper's smoothness assumptions | convergence to target in W1 | Helped |
Closest papers by meaning
- A Non-Asymptotic Analysis for Stein Variational Gradient Descent (NeurIPS 2020 · similarity 0.94)
- Long-time asymptotics of noisy SVGD outside the population limit (ICLR 2025 · similarity 0.94)
- A Finite-Particle Convergence Rate for Stein Variational Gradient Descent (NeurIPS 2023 · similarity 0.94)
- Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation (NeurIPS 2023 · similarity 0.93)
- Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent (ICLR 2025 · similarity 0.91)
- ELBOing Stein: Variational Bayes with Stein Mixture Inference (ICLR 2025 · similarity 0.89)
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.