Research map / Probabilistic and scientific modeling / Causal discovery
Efficient Least Squares for Estimating Total Effects under Linearity and Causal Sufficiency
F. Richard Guo, Emilija Perković
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 G-regression instead of adj.O (|A|=4) | adj.O · Simulation |V|=20, n=100 | relative squared error: 9.3 | Improved |
| use G-regression instead of IDA.M (|A|=4) | IDA.M · Simulation |V|=100, n=1000 | relative squared error: 1604 | Improved |
| use G-regression instead of IDA.R (|A|=4) | IDA.R · Simulation |V|=100, n=1000 | relative squared error: 432 | Improved |
| point intervention (|A|=1) versus G-regression | adj.O · Simulation |V|=20, n=100 | relative squared error: 1.3 (median 1.0) | No clear effect |
| increase number of treatments from 1 to 4 | adj.O vs G-regression · Simulation |V|=50, n=1000 | relative squared error: 1.3 -> 14 | Improved |
| estimate CPDAG with GES instead of the true CPDAG (ablation) | G-regression advantage over adj.O · Simulation |V|=20, n=100, |A|=1 | relative squared error: 1.3 -> 1.0 | Hurt |
| estimate CPDAG with GES instead of the true CPDAG (ablation) | G-regression advantage over IDA.M · Simulation |V|=20, n=100, |A|=1 | relative squared error: 20 -> 2.9 | Hurt |
| increase sample size n from 100 to 1000 | G-regression advantage over IDA.M (|A|=1) · Simulation |V|=50, true CPDAG | relative squared error: 61 -> 48 | No clear effect |
| use G-regression for joint intervention |A|=2 | adj.O estimability · Simulation |V|=20 | relative squared error: 17% | Improved |
Closest papers by meaning
- Semiparametric Inference For Causal Effects In Graphical Models With Hidden Variables (JMLR 2022 · similarity 0.89)
- Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning (ICML 2021 · similarity 0.89)
- Actively Identifying Causal Effects with Latent Variables Given Only Response Variable Observable (NeurIPS 2021 · similarity 0.89)
- Estimating Network-Mediated Causal Effects via Principal Components Network Regression (JMLR 2025 · similarity 0.89)
- Structural Causal Bottleneck Models (NeurIPS 2026 · similarity 0.88)
- Causal Effect Identification in LiNGAM Models with Latent Confounders (ICML 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.
