Research map / Probabilistic and scientific modeling / Causal discovery
Ancestral Causal Inference
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 |
|---|---|---|---|
| restrict HEJ search space using ACI ancestral constraints | HEJ · Synthetic n=6, c=4 | execution time (s): 314.29 -> 16.96 | Helped |
| restrict HEJ using ACI constraints | HEJ · Synthetic n=7, c=1 | execution time (s): 356.49 -> 36.13 | Helped |
| restrict HEJ using ACI constraints | HEJ · Synthetic n=6, c=1 | execution time (s): 15.03 -> 9.77 | Helped |
| restrict HEJ using ACI constraints | HEJ · Synthetic n=8, c=1 | execution time (s): ≥ 2500 -> 98.92 | Helped |
| use ancestral reasoning (ACI) instead of HEJ | HEJ · Synthetic n=7, c=1 | execution time: almost 3 orders of magnitude faster | Helped |
| increase independence test order from c=1 to c=4 | ACI and HEJ · Synthetic n=6 PR curves | precision-recall accuracy | No clear effect |
| add oracle background knowledge on descendants of one variable (i=1) | ACI · Synthetic n=8 | precision-recall (ancestral) | Helped |
| use ACI scoring instead of bootstrapping (C)FCI | ACI · Synthetic n=6 | precision-recall | Helped |
| use restricted HEJ for direct relations | ACI + HEJ · Synthetic n=6 direct relations | precision-recall | No clear effect |
| use weighted ancestral relations from interventional data as input | ACI · Flow cytometry | ancestral relation recovery | Helped |
| Bayesian weights instead of frequentist weights (ablation) | ACI · Synthetic n=6 | precision-recall | No clear effect |
Closest papers by meaning
- Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models (NeurIPS 2024 · similarity 0.89)
- On Causal Discovery in the Presence of Deterministic Relations (NeurIPS 2024 · similarity 0.89)
- CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery (NeurIPS 2026 · similarity 0.88)
- Causal Discovery with Fewer Conditional Independence Tests (ICML 2024 · similarity 0.88)
- Differentiable Constraint-Based Causal Discovery (NeurIPS 2025 · similarity 0.87)
- Causal Discovery via Conditional Independence Testing with Proxy Variables (ICML 2024 · similarity 0.87)
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.