Research map / Probabilistic and scientific modeling / Variational and generative sampling
Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation
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 antithetic sampling estimator instead of plain single-sample VI estimator | Gaussian q on 1-D toy target · 1-D toy target | likelihood bound E log R: -0.237 -> -0.060 | Helped |
| tighten the likelihood bound with antithetic sampling without a coupling | Gaussian q on 1-D toy target · 1-D toy target | KL to posterior: 0.237 -> 7.34 | Hurt |
| use antithetic, quasi-Monte Carlo and combined sampling instead of iid sampling for M=2,4,8 | Gaussian VI on 88 Stan models · Stan model library | ELBO and posterior variance error | Helped |
| increase number of samples M | variance-reduced sampling methods · Stan model library | improvement over iid | No clear effect |
| elliptical versus Cartesian mapping of uniform samples to Gaussian (ablation) | quasi-Monte Carlo VI · Stan model library | ELBO and variance error | Mixed |
Closest papers by meaning
- Variational Inference for Monte Carlo Objectives (ICML 2016 · similarity 0.89)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.89)
- Variational Inference for Sequential Data with Future Likelihood Estimates (ICML 2020 · similarity 0.89)
- Variational Inference via $\chi$ Upper Bound Minimization (NeurIPS 2017 · similarity 0.88)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.88)
- Least squares variational inference (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.