Research map / Learning theory and algorithms / Kernels and regression theory
On Model Identification and Out-of-Sample Prediction of PCR with Applications to Synthetic Controls
Anish Agarwal, Devavrat Shah, Dennis Shen
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 the sample size n when the number of components k equals the true rank r | PCR · Simulation 5.1, p=512, r=15 | RMSE to minimum l2-norm parameter | Improved |
| compare against true beta* instead of minimum l2-norm solution | PCR · Simulation 5.1 | RMSE | No clear effect |
| apply covariate shift between in- and out-of-sample covariates while Assumption 4.2 holds (ablation) | PCR · Simulation 5.2, four covariate distributions | out-of-sample MSE | No clear effect |
| satisfy Assumption 4.2 instead of only distributional invariance (ablation) | PCR · Simulation 5.3 | out-of-sample MSE | Improved |
| increase missing-data intensity rho in 0.4, 0.6, 0.8, 0.99 (MCAR entries) (ablation) | PCR · Simulation 5.4 | out-of-sample MSE | No clear effect |
| choose k greater than the rank r (r+5) instead of smaller (r-5) (ablation) | PCR · Appendix B misspecified k | out-of-sample MSE | Improved |
| run the Assumption 4.2 hypothesis test on Basque Country data | PCR-based synthetic control · Basque Country terrorism | test statistic vs threshold: 0.61 vs 0.15 | Hurt |
| run the Assumption 4.2 hypothesis test on California Proposition 99 data | PCR-based synthetic control · California Proposition 99 | test statistic vs threshold: 1.63 vs 0.15 | Hurt |
Closest papers by meaning
- No Double Descent in Principal Component Regression: A High-Dimensional Analysis (ICML 2024 · similarity 0.90)
- Learning with Synthetic Data via SGD in High-Dimensional Linear Regression (NeurIPS 2026 · similarity 0.81)
- Breaking the Barrier of Hard Samples: A Data-Centric Approach to Synthetic Data for Medical Tasks (ICML 2025 · similarity 0.81)
- Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression (ICML 2025 · similarity 0.81)
- Capturing the denoising effect of PCA via compression ratio (NeurIPS 2024 · similarity 0.81)
- Risk and cross validation in ridge regression with correlated samples (ICML 2025 · similarity 0.81)
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.
