Research map / Probabilistic and scientific modeling / Variational and generative sampling
Importance Weighting and Variational Inference
Justin Domke, Daniel R. Sheldon
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 |
|---|---|---|---|
| Use IWVI with self-normalized importance sampling at test time instead of standard VI | Variational inference · Clutter distributions | second-moment estimation error | Improved |
| Increase the number of importance samples M | IWVI and E-IWVI · Logistic regression: Madelon, Sonar, Mushrooms | IW-ELBO | Improved |
| Use Student-T variational distributions instead of Gaussian distributions (ablation) | IWVI · Low-dimensional inference | posterior expectation accuracy | Improved |
| Use Student-T variational distributions instead of Gaussian distributions (ablation) | IWVI · High-dimensional inference | convergence reliability | Improved |
| Use Student-T variational distributions instead of Gaussian distributions (ablation) | IWVI · Logistic regression: Madelon, Sonar, Mushrooms | convergence reliability | Improved |
| Use Student-T variational distributions instead of Gaussian distributions (ablation) | IWVI · Logistic regression | IW-ELBO | No clear effect |
| Use Student-T variational distributions instead of Gaussian distributions (ablation) | IWVI · Logistic regression | IW-ELBO across step sizes | Improved |
| Use a centered variational mean rather than a mean near one mode | IWVI with large M · One-dimensional illustrative distribution | IW-ELBO and moment error | Improved |
| Use heavy-tailed Student-T proposals rather than Gaussian proposals (ablation) | IWVI with large M · One-dimensional illustrative distribution | IW-ELBO and moment error | Improved |
Closest papers by meaning
- Hierarchical Importance Weighted Autoencoders (ICML 2019 · similarity 0.89)
- Forward $\chi^2$ Divergence Based Variational Importance Sampling (ICLR 2024 · similarity 0.88)
- Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference (NeurIPS 2026 · similarity 0.88)
- Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution (ICML 2024 · similarity 0.87)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.87)
- Revisiting Unbiased Implicit Variational Inference (ICML 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.
