Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Variational Bayesian Monte Carlo with Noisy Likelihoods
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 global VIQR rather than pointwise uncertainty sampling (NPRO) | VBMC · Noisy-inference benchmark | posterior and model-evidence approximation quality | Helped |
| Use VIQR rather than EIG | VBMC · Noisy-inference benchmark | posterior and model-evidence approximation quality | Helped |
| Use VIQR rather than IMIQR | VBMC · Noisy-inference benchmark | algorithmic overhead per likelihood evaluation: 5.5 ± 0.5 vs 1.5 ± 0.1 (Ricker); 5.1 ± 0.3 vs 1.5 ± 0.1 (aDDM); 5.8 ± 0.6 vs 1.8 ± 0.2 (Timing); 5.6 ± 0.3 vs 2.0 ± 0.2 | Helped |
| Use VBMC-IMIQR or VBMC-VIQR rather than VBMC-EIG | VBMC · Rodent 2AFC and Bayesian timing | posterior and model-evidence approximation quality | Helped |
| Use VBMC-IMIQR or VBMC-VIQR rather than GP-IMIQR | Noisy surrogate-based inference · Rodent 2AFC, Neuronal selectivity, and Bayesian timing | posterior approximation quality | Helped |
| Use VBMC-VIQR rather than GP-IMIQR | Noisy surrogate-based inference · Ricker | algorithmic overhead per likelihood evaluation: 15.6 ± 0.9 vs 1.5 ± 0.1 | Helped |
| Use VIQR or IMIQR instead of pointwise uncertainty sampling | VBMC · Noisy likelihoods as observation noise increases | posterior and model-evidence approximation quality | Helped |
| Increase observation noise | VBMC-VIQR · Emulated-noise benchmark | posterior and model-evidence approximation quality: σ_obs ∈ [0, 7] | Hurt |
| Use imprecise observation-noise estimates | VBMC-VIQR · Emulated-noise benchmark | performance: ∼ 25% with σ_σ up to 0.4 | Hurt |
| Apply variational whitening to rotate and rescale inference coordinates (ablation) | VBMC · Correlated posterior inference | posterior approximation quality | Helped |
Closest papers by meaning
- Variational Bayesian Monte Carlo (NeurIPS 2018 · similarity 0.92)
- Variational Bayes under Model Misspecification (NeurIPS 2019 · similarity 0.88)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.85)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.85)
- SoftCVI: Contrastive variational inference with self-generated soft labels (ICLR 2025 · similarity 0.84)
- Online Variational Sequential Monte Carlo (ICML 2024 · similarity 0.84)
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.