Research map / Probabilistic and scientific modeling / Variational and generative sampling
Extending Mean-Field Variational Inference via Entropic Regularization: Theory and Computation
Bohan Wu, David M. Blei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add entropic expressivity regularization (Xi-VI, small lambda) to mean-field VI | mean-field VI · Eight Schools | posterior dependence between theta_1 and theta_7 | Improved |
| add Xi-VI instead of MFVI for max and min treatment effect credible intervals | MFVI, NFVI, SVGD, full-rank ADVI · Eight Schools | 95% credible interval width and coverage | Improved |
| increase lambda beyond D (more regularization toward mean-field) (ablation) | Xi-VI · Laplace linear regression (n=100, d=12) | W2 error and runtime | Mixed |
| increase lambda from below 1 to above 10 (ablation) | Xi-VI · Eight Schools | approximation error vs runtime | Mixed |
| increase number of pseudomarginal points N (ablation) | Xi-VI · Laplace linear regression (lambda=10) | approximation accuracy | No clear effect |
| use overdispersed pseudomarginals rather than underdispersed (ablation) | Xi-VI one-step EOT correction · Eight Schools | sample dependency structure | Improved |
| compare normalizing-flow VI with Xi-VI | Xi-VI · Eight Schools | W2 and KL distance | No clear effect |
Closest papers by meaning
- Advances in Variational Inference (TPAMI 2018 · similarity 0.93)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.91)
- Mean-Field Variational Inference via Wasserstein Gradient Flow (JMLR 2025 · similarity 0.90)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.90)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.90)
- Least squares variational inference (NeurIPS 2025 · similarity 0.90)
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.
