Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Approximate Bayesian Computation with Domain Expert in the Loop
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 expert feedback to exclude statistics that produce misspecified ABC posteriors | Regression-ABC for the radio propagation model · Radio propagation model, ζ > 0 | posterior characterization | Helped |
| Include expert feedback in statistics selection | Regression-ABC · g-and-k, N_sim ≤ 350 | KL divergence to reference ABC posterior | Helped |
| Include expert feedback in statistics selection | Regression-ABC · g-and-k, N_sim ≥ 400 | KL divergence to reference ABC posterior | No clear effect |
| Use utility-maximizing rather than random query acquisition | HITL-ABC · g-and-k | average number of expert feedback: 10.1 vs 13.8; 8.5 vs 13.6; 8.3 vs 13.4; 6.3 vs 13.3; 6.0 vs 13.1; 6.3 vs 13.4 | Helped |
| Increase feedback reliability π | HITL-ABC · Gaussian toy problem, ρ = 0.5 | runs selecting sufficient statistics: 27% to 100% | Helped |
| Vary the prior inclusion probability ρ | HITL-ABC · Gaussian toy problem, π = 0.95 | runs selecting sufficient statistics: 91% to 95% | No clear effect |
| Increase stopping threshold δ | HITL-ABC · Gaussian toy problem | average number of expert feedback: 3.04 to 2.17 | Helped |
Closest papers by meaning
- Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation (NeurIPS 2016 · similarity 0.91)
- Learning Likelihood-Free Reference Priors (ICML 2025 · similarity 0.86)
- Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models (NeurIPS 2025 · similarity 0.85)
- Scalable Bayesian Learning with posteriors (ICLR 2025 · similarity 0.84)
- Do Bayesian Neural Networks Actually Behave Like Bayesian Models? (ICML 2025 · similarity 0.84)
- ABC3: Active Bayesian Causal Inference with Cohn Criteria in Randomized Experiments (AAAI 2025 · similarity 0.83)
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.