Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Variational Bayesian Monte Carlo
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 |
|---|---|---|---|
| Combine variational inference with active-sampling Bayesian quadrature using GP surrogates | VBMC · Synthetic likelihoods, D=2, 4, 6, 8, 10 | posterior gsKL and absolute LML error | Helped |
| Use VBMC rather than the tested alternatives | Neuronal model, two datasets (D=7) · Neuronal model | posterior gsKL and absolute LML error | Helped |
| Use prospective uncertainty sampling instead of vanilla uncertainty sampling (ablation) | VBMC · Neuronal model | convergence speed | Helped |
| Use prospective uncertainty sampling instead of vanilla uncertainty sampling (ablation) | VBMC · Synthetic likelihoods | posterior gsKL and absolute LML error | No clear effect |
| Use vanilla uncertainty sampling instead of prospective uncertainty sampling (ablation) | VBMC · Neuronal model | convergence speed | Hurt |
| Train a GP on samples collected by VBMC rather than samples collected by other methods | GP posterior approximation · Neuronal model | posterior gsKL | Helped |
| Estimate the marginal likelihood with WSABI-L using samples collected by VBMC | WSABI-L · Neuronal model | absolute LML error | Helped |
| Replace the negative quadratic GP mean with a constant mean (ablation) | VBMC GP surrogate · Posterior and evidence inference | integrability of the exponentiated GP predictive mean | Hurt |
| Use a deterministic entropy approximation instead of Monte Carlo entropy estimation (ablation) | VBMC variational objective · Posterior inference | performance | Mixed |
Closest papers by meaning
- 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)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.89)
- Bayesian Online Natural Gradient (BONG) (NeurIPS 2024 · similarity 0.89)
- SoftCVI: Contrastive variational inference with self-generated soft labels (ICLR 2025 · similarity 0.89)
- VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.89)
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.