Research map / Probabilistic and scientific modeling / Causal discovery
Testing Independence Between Linear Combinations for Causal Discovery
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 |
|---|---|---|---|
| Replace KCIT-based residual independence testing with FRCIT's kurtosis-curve comparison | ReCIT in PC causal discovery · real-world causal structures | F1: PCFRCIT achieves the best F1 score on almost all structures | Helped |
| Use FRCIT instead of ReCIT for residual independence testing | ReCIT · independence testing, sample size 2000 | elapsed time (s): 2.9821 -> 0.0970 | Helped |
| Use FRCIT instead of ReCIT | ReCIT · independence testing, Case I and Case II | Type I and Type II error rates | Helped |
| Use PCFRCIT rather than PCKCIT | PC causal discovery · random DAG causal skeleton and PDAG | F1: about 0.007; about 0.014 | Helped |
| Increase the number of noise variables | FRCIT and ReCIT · Case II, dependent uncorrelated linear combinations | Type II error rate | Hurt |
Closest papers by meaning
- Causal Discovery via Conditional Independence Testing with Proxy Variables (ICML 2024 · similarity 0.92)
- PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data (NeurIPS 2026 · similarity 0.89)
- On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery (ICML 2024 · similarity 0.88)
- A Conditional Independence Test in the Presence of Discretization (ICLR 2025 · similarity 0.87)
- Testing Causal Models with Hidden Variables in Polynomial Delay via Conditional Independencies (AAAI 2025 · similarity 0.87)
- Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes (ICLR 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.