Research map / Learning theory and algorithms / Submodular and game algorithms
Budgeted Experiment Design for Causal Structure Learning
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 |
|---|---|---|---|
| Select intervention targets greedily by expected marginal edge-orientation gain instead of choosing them randomly | Ran-GrID · Synthetic chordal DAGs | discovered edge ratio | Helped |
| Select intervention targets greedily by expected marginal edge-orientation gain instead of choosing the highest-degree variables | Ran-GrID · Synthetic chordal DAGs | discovered edge ratio | Helped |
| Use Ran-GrID rather than brute-force search for intervention selection | Synthetic chordal DAGs, order 10, budget k=2 · Synthetic chordal DAGs, order 10, budget k=2 | running time: 216 seconds vs greater than 6000 seconds | Helped |
| Use Ran-GrID rather than the optimal intervention set | Synthetic chordal DAGs, order 10, budget k=2 · Synthetic chordal DAGs, order 10, budget k=2 | discovered edge ratio: 0.9 vs 0.916 | Hurt |
| Use five single-variable interventions selected by the Improved Greedy Algorithm | DREAM 3 GRNs · DREAM 3 GRNs, five networks, order 100, budget k=5 | discovered edge ratio: at least 0.65 | Helped |
| Use lazy marginal-gain evaluations instead of evaluating every remaining variable in every greedy round | Improved Greedy Algorithm · Causal structure learning | performance speedup: orders of magnitude | Helped |
Closest papers by meaning
- Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning (NeurIPS 2021 · similarity 0.93)
- Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models (NeurIPS 2025 · similarity 0.92)
- Adaptive Online Experimental Design for Causal Discovery (ICML 2024 · similarity 0.89)
- Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits (NeurIPS 2024 · similarity 0.88)
- Sample Efficient Bayesian Learning of Causal Graphs from Interventions (NeurIPS 2024 · similarity 0.88)
- Linear Causal Bandits: Unknown Graph and Soft Interventions (NeurIPS 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.