Research map / Probabilistic and scientific modeling / Causal discovery
A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models
Alexander Gilbert Reisach, Myriam Tami, Christof Seiler, Antoine Chambaz, Sebastian Weichwald
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 |
|---|---|---|---|
| Sort variables by increasing R² and regress each on its predecessors | R²-SortnRegress on protein signalling data · Protein signalling dataset | SID: 48.13 vs 43.70 | Hurt |
| Sort variables by increasing R² and regress each on its predecessors | R²-SortnRegress on protein signalling data · Protein signalling dataset | SHD: 14.43 vs 11.40 | Hurt |
| Use increasing R² as the ordering criterion instead of random regression | Regression-based causal discovery on protein signalling data · Protein signalling dataset | SID: 52.57 vs 48.13 | Improved |
| Use increasing R² as the ordering criterion instead of random regression | Regression-based causal discovery on protein signalling data · Protein signalling dataset | SHD: 16.20 vs 14.43 | Improved |
| Use lower absolute edge weights | Linear ANM simulations with R²-SortnRegress · Simulated ER graphs | SID | Mixed |
| Use lower absolute edge weights | Linear ANM simulations with R²-SortnRegress · Simulated scale-free graphs | SID | Mixed |
| Increase the edge-weight distribution's expected log absolute weight | Linear ANM simulations · Random graphs | R²-sortability | Improved |
| Use exponentially distributed rather than bounded noise standard deviations | Linear ANM simulations · Random graphs | R²-sortability: ≈ 0.65 vs ≈ 0.8 | Hurt |
| Increase average in-degree | Linear ANM simulations · Erdős–Rényi graphs | R²-sortability | Improved |
| Use scale-free rather than Erdős–Rényi graph structure | Linear ANM simulations · Random graphs | R²-sortability | Improved |
Closest papers by meaning
- Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models (NeurIPS 2024 · similarity 0.89)
- Standardizing Structural Causal Models (ICLR 2025 · similarity 0.89)
- Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models (ICML 2025 · similarity 0.88)
- Ordering-Based Causal Discovery for Linear and Nonlinear Relations (NeurIPS 2024 · similarity 0.87)
- A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery (ICLR 2025 · similarity 0.87)
- When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery (NeurIPS 2025 · similarity 0.86)
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.
