Research map / Probabilistic and scientific modeling / Causal discovery
Switching Regression Models and Causal Inference in the Presence of Discrete Latent Variables
Rune Christiansen, Jonas Peters
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 |
|---|---|---|---|
| enforce equal error variances across hidden states (sigma_Y1^2 = sigma_Y2^2) (ablation) | ICPH · Simulated SCM with binary hidden variable | identification of S*: sigma_Y1^2 = sigma_Y2^2 vs sigma_Y1^2, sigma_Y2^2 >= 10^{-4} | Improved |
| increase sample size | ICPH · Simulated SCM with binary hidden variable | identification of S*: n from 100 to 500 | Improved |
| lower GMEP (harder hidden-state estimation) | adjusted confidence regions · Simulated SR model, n=100 | empirical coverage of 95% confidence regions | Hurt |
| use ICPH instead of k-means ICP and JCI-PC | causal discovery · Simulated SCM with binary hidden variable | level and power | Improved |
| initialize optimizer at the true parameter values instead of data-driven (ablation) | NLM optimizer · Simulated SR model, n=100 | likelihood score: less than 0.2% | No clear effect |
| use EM instead of NLM optimizer (ablation) | ICPH · Simulated data | results and runtime: computation time larger by approximately a factor of 6 | No clear effect |
Closest papers by meaning
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.90)
- Latent Variable Causal Discovery under Selection Bias (ICML 2025 · similarity 0.89)
- Bivariate Causal Discovery using Bayesian Model Selection (ICML 2024 · similarity 0.89)
- Causal learning with the invariance principle (NeurIPS 2026 · similarity 0.89)
- Discovering Mixtures of Structural Causal Models from Time Series Data (ICML 2024 · similarity 0.88)
- A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables (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.
