Research map / Probabilistic and scientific modeling / Treatment effects
Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference
Valentyn Melnychuk, Vahid Balazadeh, Stefan Feuerriegel, Rahul G Krishnan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add one-step posterior correction (MP-OSPC) to TabPFN+copula (rho=0.25) MP-plug-in (ablation) | TabPFN+copula MP · ACIC-2016 | % runs best by d_TV: 14.81 -> 33.25 | Improved |
| add one-step posterior correction (MP-OSPC) to TabPFN+copula (rho=0.5) MP-plug-in (ablation) | TabPFN+copula MP · ACIC-2016 | % runs best by d_TV: 14.29 -> 37.66 | Improved |
| add one-step posterior correction (MP-OSPC) to TabPFN+copula (rho=0.5) MP-plug-in (ablation) | TabPFN+copula MP · ACIC-2016 | % runs best by d_KS: 22.73 -> 22.73 | No clear effect |
| add MP-OSPC (rho=0.25) to CausalPFN (T=0.5) (ablation) | CausalPFN · ACIC-2016 | % runs best by d_TV: 54.16 -> 18.70 | Hurt |
| add MP-OSPC (rho=0.25) to CausalPFN (T=0.5) (ablation) | CausalPFN · ACIC-2016 | % runs best by d_KS: 30.95 -> 45.24 | Improved |
| add MP-OSPC (rho=0.25) to CausalPFN (T=0.1) (ablation) | CausalPFN · ACIC-2016 | % runs best by d_KS: 31.65 -> 49.37 | Improved |
| add MP-OSPC (rho=0.5) to CausalPFN (T=0.1) (ablation) | CausalPFN · ACIC-2016 | % runs best by d_KS: 31.65 -> 18.99 | Hurt |
| use MP-OSPC instead of plug-in estimators | TabPFN and CausalPFN · synthetic data (varying n_train, d_x) | d_TV to A-IPTW | Improved |
| increase training set size beyond 5000 | TabPFN+copula MP · synthetic L2-concentration | R2 hat | Hurt |
| use TabPFN+copula (smooth) as MP variant (ablation) | MP-OSPC · L2-concentration check | R2 hat | Improved |
| vary copula correlation rho (ablation) | MP-OSPC · ATE estimation | d_TV / d_KS | No clear effect |
Closest papers by meaning
- Do-PFN: In-Context Learning for Causal Effect Estimation (NeurIPS 2025 · similarity 0.90)
- CausalPFN: Amortized Causal Effect Estimation via In-Context Learning (NeurIPS 2025 · similarity 0.87)
- Generalized Bayes for Causal Inference (NeurIPS 2026 · similarity 0.87)
- Position: The Future of Bayesian Prediction Is Prior-Fitted (ICML 2025 · similarity 0.87)
- Causally Consistent Normalizing Flow (AAAI 2025 · similarity 0.86)
- Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounders (AAAI 2024 · similarity 0.86)
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.
