Research map / Probabilistic and scientific modeling / Causal discovery
The Reduced PC-Algorithm: Improved Causal Structure Learning in Large Random Networks
Arjun Sondhi, Ali Shojaie
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 |
|---|---|---|---|
| use rPC-approx instead of PC-Algorithm | PC-Algorithm · Power law DAGs | true vs false positive rate (pROC) | Improved |
| use rPC instead of PC-Algorithm | PC-Algorithm · Erdos-Renyi DAGs | true vs false positive rate (pROC) | No clear effect |
| use rPC-approx instead of rPC-full (exhaustive separating-set search) | rPC · simulated DAGs | accuracy | No clear effect |
| use rPC-approx instead of PC-Algorithm | PC-Algorithm · Power law p=500 n=200 | runtime ratio: 100 -> 0.36 | Improved |
| use rPC-full instead of PC-Algorithm | PC-Algorithm · Erdos-Renyi p=500 n=200 | runtime ratio: 1 -> 23.25 | Hurt |
| use rPC-approx instead of PC-Algorithm | PC-Algorithm · Erdos-Renyi p=100 n=200 | runtime ratio: 0.98 | No clear effect |
| tune eta by BIC over 1 to 4 in rPC-approx | rPC-approx · power law DAGs | true vs false positive rate (pROC) | Improved |
| use rPC-approx instead of PC-Algorithm | PC-Algorithm · Prostate cancer TCGA network | hub genes identified: 6 -> 19 | Improved |
| path faithfulness instead of restricted strong faithfulness | PC-Algorithm assumption · Power law, expected degree 2, p=20 | probability condition satisfied: 0.54 -> 0.85 | Improved |
| path faithfulness instead of restricted strong faithfulness | PC-Algorithm assumption · Erdos-Renyi, expected degree 5, p=10 | probability condition satisfied: 0.10 -> 0.61 | Improved |
| path faithfulness instead of restricted strong faithfulness | PC-Algorithm assumption · dense graphs, p=30 | probability condition satisfied: 0 -> 0.01 | No clear effect |
Closest papers by meaning
- Structure Learning for Directed Trees (JMLR 2022 · similarity 0.89)
- Federated Learning of Generalized Linear Causal Networks (TPAMI 2024 · similarity 0.89)
- Permutation-based Causal Inference Algorithms with Interventions (NeurIPS 2017 · similarity 0.88)
- Learning causal graphs via nonlinear sufficient dimension reduction (JMLR 2025 · similarity 0.88)
- Dynamical Causality Under Latent Confounders for Biological Network Reconstruction (TPAMI 2026 · similarity 0.88)
- Learning the Causal Structure of Networked Dynamical Systems under Latent Nodes and Structured Noise (AAAI 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.
