Research map / Probabilistic and scientific modeling / Variational and generative sampling
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
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 an intermediate β rather than β=0 or β=1 (ablation) | Langevin–SGVI hybrid · Bayesian logistic regression (a1a, australian, ionosphere, sonar) | MMD | Helped |
| Use an intermediate β rather than either endpoint (ablation) | Langevin–SGVI hybrid · Toy 2-dimensional distributions | MMD | No clear effect |
| Set β=0, removing injected Langevin noise and recovering variational optimization (ablation) | Langevin–SGVI hybrid · Toy 2-dimensional distributions | MMD | Mixed |
| Set β=1, recovering Langevin dynamics (ablation) | Langevin–SGVI hybrid · Toy 2-dimensional distributions | MMD | Mixed |
Closest papers by meaning
- Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics (ICML 2020 · similarity 0.94)
- A Contrastive Divergence for Combining Variational Inference and MCMC (ICML 2019 · similarity 0.93)
- Structured Stochastic Gradient MCMC (ICML 2022 · similarity 0.92)
- 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 0.89)
- Particle Semi-Implicit Variational Inference (NeurIPS 2024 · similarity 0.88)
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.