Research map / Probabilistic and scientific modeling / Treatment effects
ScoreMatchingRiesz: Score Matching for Debiased Machine Learning and Policy Path Estimation
Masahiro Kato
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 |
|---|---|---|---|
| replace Riesz regression with Data-SMR (denoising score matching) | AME estimation · synthetic AME simulation | MSE: 10.076 -> 0.161 | Improved |
| replace Riesz regression with Data-SMR | APE estimation · synthetic APE simulation (delta=1) | MSE: 74.918 -> 0.486 | Improved |
| use Time-SMR instead of Data-SMR when data score suffices | APE estimation · synthetic APE simulation | 95% coverage: 89.4% -> 75.0% | Hurt |
| use Time-SMR instead of Data-SMR | AME estimation · synthetic AME simulation | MSE: 0.161 -> 0.637 | Hurt |
| add joint data and time score training (ablation) | Time-SMR · non-pushforward stochastic-intervention design (APE) | APE MSE: 7.392 -> 1.254 | Improved |
| add joint training to Time-SMR (ablation) | Time-SMR · IHDP semi-synthetic ATE | RMSE: 1.571 -> 1.478 | Improved |
| use Time-SMR instead of direct ratio-fitting baselines (SQ-Riesz) | ATE estimation · IHDP semi-synthetic ATE | RMSE: 27.954 -> 1.571 | Improved |
| use Time-SMR instead of BKL-Riesz | ATE estimation · IHDP semi-synthetic ATE | RMSE: 84.072 -> 1.571 | Improved |
| use Time-SMR instead of Riesz regression (AME) | AME estimation · synthetic AME simulation | MSE: 10.076 -> 0.637 | Improved |
Closest papers by meaning
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization (ICLR 2024 · similarity 0.83)
- Scores for Learning Discrete Causal Graphs with Unobserved Confounders (AAAI 2024 · similarity 0.83)
- Off-policy estimation with adaptively collected data: the power of online learning (NeurIPS 2024 · similarity 0.83)
- Efficient Policy Evaluation Across Multiple Different Experimental Datasets (NeurIPS 2024 · similarity 0.83)
- Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding (NeurIPS 2024 · similarity 0.82)
- Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness (ICML 2024 · similarity 0.82)
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.
