Research map / Probabilistic and scientific modeling / Causal discovery
On Efficient Adjustment in Causal Graphs
Janine Witte, Leonard Henckel, Marloes H. Maathuis, Vanessa Didelez
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 |
|---|---|---|---|
| replace the parent set of X with the O-set as adjustment set in IDA | semi-local IDA · Simulation, true CPDAG (p=100, d=4, n=1000) | relative MSE (geometric mean): 0.40 | Improved |
| replace the parent set of X with the O-set as adjustment set in IDA | semi-local IDA · Simulation, true CPDAG (p=10, d=4, n=100) | relative MSE (geometric mean): 0.76 | Improved |
| replace the parent set of X with the O-set in IDA, using a GES-estimated CPDAG | semi-local IDA · Simulation, estimated CPDAG (p=100, d=4, n=1000) | relative MSE (geometric mean): 0.72 | Improved |
| replace the parent set of X with the O-set in IDA, using a GES-estimated CPDAG | semi-local IDA · Simulation, estimated CPDAG (p=10, d=2, n=100) | relative MSE (geometric mean): 1.06 | Hurt |
| increase number of nodes from p=10 to p=100 (true CPDAG, d=4, n=1000) | optimal IDA · Simulation, true CPDAG | relative MSE (geometric mean): 0.75 -> 0.40 | Improved |
| increase expected neighbours from d=2 to d=4 (true CPDAG, p=100, n=1000) | optimal IDA · Simulation, true CPDAG | relative MSE (geometric mean): 0.54 -> 0.40 | Improved |
| increase sample size from n=100 to n=1000 (estimated CPDAG, p=100, d=4) | optimal IDA · Simulation, estimated CPDAG | relative MSE (geometric mean): 0.90 -> 0.72 | Improved |
| use estimated CPDAG instead of true CPDAG | optimal IDA · Simulation, sparse graph (p=10, d=1, n=100) | relative MSE (geometric mean): 0.71 -> 1.04 | Hurt |
| use estimated CPDAG instead of true CPDAG | optimal IDA · Simulation (p=100, d=4, n=1000) | relative MSE (geometric mean): 0.40 -> 0.72 | Hurt |
| optimal IDA vs local IDA in high-dimensional sparse graphs, true CPDAG | optimal IDA · Simulation, sparse graph, true CPDAG (p=250, d=1, n=100) | relative MSE (geometric mean): 0.60 | Improved |
| optimal IDA vs local IDA in high-dimensional sparse graphs, estimated CPDAG | optimal IDA · Simulation, sparse graph, estimated CPDAG (p=500, d=1, n=100) | relative MSE (geometric mean): 1.16 | No clear effect |
Closest papers by meaning
- Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference (NeurIPS 2024 · similarity 0.90)
- Linear-Time Algorithms for Front-Door Adjustment in Causal Graphs (AAAI 2024 · similarity 0.89)
- Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation (NeurIPS 2026 · similarity 0.88)
- Unified Covariate Adjustment for Causal Inference (NeurIPS 2024 · similarity 0.88)
- Doubly robust identification of treatment effects from multiple environments (ICLR 2025 · similarity 0.88)
- Identifying Macro Conditional Independencies and Macro Total Effects in Summary Causal Graphs with Latent Confounding (AAAI 2025 · 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.
