Research map / Learning theory and algorithms / Prediction and decision losses
Finite Population Regression Adjustment and Non-asymptotic Guarantees for Treatment Effect Estimation
Mehrdad Ghadiri, David Arbour, Tung Mai, Cameron N Musco, Anup Rao
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 cross-adjustment with a random-vector linear regressor instead of uniform HT assignment | ATE estimator · Boston | ATE abs error: 1.736 -> 0.628 | Improved |
| use proposed estimator instead of uniform HT | ATE estimator · IHDP | ATE abs error: 0.272 -> 0.040 | Improved |
| use proposed estimator instead of uniform HT | ATE estimator · Twins | ATE abs error: 1.351e−3 -> 1.218e−3 | Improved |
| use proposed estimator versus 4-vectors cross-adjustment | ATE estimator · Boston | ATE abs error: 1.677 -> 0.628 | Improved |
| use proposed estimator versus 4-vectors approach | ATE estimator · IHDP | ATE abs error: 0.264 -> 0.040 | Improved |
| use proposed estimator versus biased leverage score method | ATE estimator · IHDP | ATE abs error: 0.536 -> 0.040 | Improved |
| proposed estimator versus GSW design | ATE estimator · IHDP | ATE abs error: 0.042 -> 0.040 | No clear effect |
| proposed estimator versus GSW on synthetic ATE data | ATE estimator · synthetic ATE | relative ATE error | Hurt |
| biased classic regression adjustment versus proposed unbiased estimator | ATE estimator · Boston | ATE abs error: 0.333 -> 0.628 | Hurt |
| proposed ITE estimator versus leverage score based | ITE estimator · IHDP | ITE error: 2.449 -> 1.765 | Improved |
| proposed ITE estimator versus leverage score based | ITE estimator · Twins | ITE error: 0.156 -> 0.156 | No clear effect |
| proposed ITE estimator versus leverage score based | ITE estimator · Boston | ITE error: 0.827 -> 7.654 | Hurt |
Closest papers by meaning
- Beyond the Average: Distributional Causal Inference under Imperfect Compliance (NeurIPS 2025 · similarity 0.87)
- Active Treatment Effect Estimation via Limited Samples (ICML 2025 · similarity 0.87)
- Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction (ICML 2024 · similarity 0.87)
- On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization (ICML 2025 · similarity 0.86)
- Asymptotically Optimal and Computationally Efficient Average Treatment Effect Estimation in A/B testing (ICML 2024 · similarity 0.85)
- Efficient Adaptive Experimentation with Noncompliance (NeurIPS 2025 · similarity 0.85)
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.
