Research map / Probabilistic and scientific modeling / Treatment effects
Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression
Seok-Jin Kim, Kaizheng Wang
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 |
|---|---|---|---|
| add second-stage smoothing on pseudo-outcomes (vs plug-in marginalization) (ablation) | Two-stage KRR · Synthetic confounded (n=1000) | MISE x100: 9.87 -> 6.22 | Improved |
| add second-stage smoothing on pseudo-outcomes (vs plug-in marginalization) (ablation) | Two-stage KRR · Synthetic confounded (n=500) | MISE x100: 11.81 -> 8.40 | Improved |
| correct for confounding via first-stage outcome model and pseudo-outcomes (vs direct regression on treatment) | Two-stage KRR · Synthetic confounded (n=1000) | MISE x100: 14.52 -> 6.22 | Improved |
| correct for confounding via first-stage outcome model and pseudo-outcomes (vs direct regression on treatment) | Two-stage KRR · Synthetic confounded (n=500) | MISE x100: 14.84 -> 8.40 | Improved |
| increase sample size from 500 to 1000 | Two-stage KRR · Synthetic confounded | MISE x100: 8.40 -> 6.22 | Improved |
| add second-stage smoothing (vs Plug-in LOOCV) (ablation) | Two-stage KRR · Job Corps semi-real | MISE: 1.6197 -> 1.2466 | Improved |
| use two-stage KRR instead of direct regression | Two-stage KRR · Job Corps semi-real | MISE: 1.6970 -> 1.2466 | Improved |
| use two-stage KRR instead of DML with GRF nuisance | Two-stage KRR · Job Corps semi-real | MISE: 2.42 -> 1.24 | Improved |
Closest papers by meaning
- Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing (AAAI 2024 · similarity 0.89)
- Continuous Treatment Effects with Surrogate Outcomes (ICML 2024 · similarity 0.88)
- Learning Representations of Instruments for Partial Identification of Treatment Effects (ICML 2025 · similarity 0.88)
- Doubly robust identification of treatment effects from multiple environments (ICLR 2025 · similarity 0.87)
- Learning Shadow Variable Representation for Treatment Effect Estimation under Collider Bias (ICML 2024 · similarity 0.87)
- Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data (NeurIPS 2025 · similarity 0.87)
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.
