Research map / Probabilistic and scientific modeling / Causal discovery
Learning Instrumental Variables with Structural and Non-Gaussianity Assumptions
Ricardo Silva, Shohei Shimizu
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 |
|---|---|---|---|
| increase sample size from N=1000 to N=10000 | IV-TETRAD+ · Synthetic IV study, confounding 0.125 | Table 2 first value: 0.23 -> 0.07 | Improved |
| increase sample size from N=1000 to N=10000 | IV-TETRAD+ · Synthetic IV study, confounding 0.25 | Table 2 first value: 0.56 -> 0.10 | Improved |
| increase sample size from N=1000 to N=10000 | SISVIVE · Synthetic IV study, confounding 0.125 | Table 2 first value: 0.34 -> 0.31 | No clear effect |
| increase sample size from N=1000 to N=10000 | SISVIVE · Synthetic IV study, confounding 0.25 | Table 2 first value: 0.64 -> 0.68 | No clear effect |
| increase sample size from N=1000 to N=10000 | NAIVE1 · Synthetic IV study, confounding 0.125 | Table 2 first value: 0.25 -> 0.25 | No clear effect |
| use IV-TETRAD+ instead of SISVIVE at N=10000 | IV-TETRAD+ · Synthetic IV study, confounding 0.125 | Table 2 first value: 0.31 -> 0.07 | Improved |
| use IV-TETRAD+ instead of SISVIVE at N=10000 | IV-TETRAD+ · Synthetic IV study, confounding 0.25 | Table 2 first value: 0.68 -> 0.10 | Improved |
| use IV-TETRAD+ instead of NAIVE2 at N=10000 | IV-TETRAD+ · Synthetic IV study, confounding 0.125 | Table 2 first value: 0.15 -> 0.07 | Improved |
| use IV-TETRAD+ instead of SISVIVE at N=1000 | IV-TETRAD+ · Synthetic IV study, confounding 0.25 | Table 2 first value: 0.64 -> 0.56 | Hurt |
| double confounding strength from 0.125 to 0.25 | NAIVE1 · Synthetic IV study, N=10000 | Table 2 first value: 0.25 -> 0.50 | Hurt |
Closest papers by meaning
- Conditional Common Entropy for Instrumental Variable Testing and Partial Identification (ICML 2024 · similarity 0.89)
- Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models (ICML 2025 · similarity 0.88)
- Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants (AAAI 2024 · similarity 0.88)
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.88)
- Identifying Causal Effects Under Functional Dependencies (NeurIPS 2024 · similarity 0.88)
- Conditional Instrumental Variable Regression with Representation Learning for Causal Inference (ICLR 2024 · 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.
