Research map / Probabilistic and scientific modeling / Causal discovery
Estimating Causal Structure Using Conditional DAG Models
Chris. J. Oates, Jim Q. Smith, Sach Mukherjee
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 CDAG estimator (secondary variables with CDAG structure) instead of DAG on primary variables only | score-based DAG estimator · Simulated, theta=0, p=15, n=1000 | mean SHD: 6.3 ± 1.5 -> 0.8 ± 0.25 | Improved |
| enforce CDAG structure instead of plain DAG2 on all variables | DAG2 · Simulated, theta=0, p=15, n=1000 | mean SHD: 8.2 ± 0.92 -> 0.8 ± 0.25 | Improved |
| use CDAG instead of DAG at strong secondary covariation | score-based DAG estimator · Simulated, theta=0.99, p=15, n=1000 | mean SHD: 17 ± 1.8 -> 0.7 ± 0.4 | Improved |
| use CDAG instead of DAG at small sample size | score-based DAG estimator · Simulated, theta=0, p=5, n=10 | mean SHD: 2.9 ± 0.48 -> 3.4 ± 0.56 | Hurt |
| use CDAG instead of DAG at n=100 | score-based DAG estimator · Simulated, theta=0, p=10, n=100 | mean SHD: 8.2 ± 0.99 -> 2.8 ± 0.51 | Improved |
| introduce misspecified edges X_i -> Y_j violating CDAG assumptions | CDAG estimator · Simulated, theta=0, p=15, n=1000 | mean SHD | Mixed |
Closest papers by meaning
- Counting and Sampling from Markov Equivalent DAGs Using Clique Trees (AAAI 2019 · similarity 0.91)
- Direct Estimation of Differences in Causal Graphs (NeurIPS 2018 · similarity 0.91)
- Causal Effect Identification in Cluster DAGs (AAAI 2023 · similarity 0.90)
- Local Identifying Causal Relations in the Presence of Latent Variables (ICML 2025 · similarity 0.88)
- Coarsening Linear Non-Gaussian Causal Models with Cycles (NeurIPS 2026 · similarity 0.88)
- Identifying Macro Conditional Independencies and Macro Total Effects in Summary Causal Graphs with Latent Confounding (AAAI 2025 · similarity 0.88)
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.
