Research map / Probabilistic and scientific modeling / Variational and generative sampling
Provable Gradient Variance Guarantees for Black-Box Variational Inference
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 a numerically optimized sampling distribution instead of uniform sampling | Subsampled reparameterization gradient estimation · Regression and classification datasets | gradient variance: 1.5x and 10x higher | Helped |
| Use a more careful sampling distribution rather than uniform sampling | Subsampled reparameterization gradient estimation · Regression and classification datasets | empirical gradient variance | Helped |
| Use a more careful sampling distribution rather than uniform sampling | Subsampled reparameterization gradient estimation · Regression and classification datasets | true gradient variance | Helped |
| Use matrix smoothness instead of scalar smoothness | Variance bounds for reparameterization gradients · Linear regression models | variance-bound tightness | Helped |
| Use matrix smoothness instead of scalar smoothness | Variance bounds for reparameterization gradients · Logistic regression models | variance-bound tightness | Helped |
| Use full-dataset batch estimation instead of data subsampling | Reparameterization gradient estimation · Regression and classification datasets | gradient variance | Helped |
Closest papers by meaning
- Provable convergence guarantees for black-box variational inference (NeurIPS 2023 · similarity 0.94)
- Provable Smoothness Guarantees for Black-Box Variational Inference (ICML 2020 · similarity 0.91)
- Marginalized Stochastic Natural Gradients for Black-Box Variational Inference (ICML 2021 · similarity 0.91)
- Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference (NeurIPS 2025 · similarity 0.89)
- Understanding Stochastic Natural Gradient Variational Inference (ICML 2024 · similarity 0.87)
- Natural Gradient VI: Guarantees for Non-Conjugate Models (NeurIPS 2025 · similarity 0.87)
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.