Research map / Probabilistic and scientific modeling / Treatment effects
Treatment Effect Estimation with Data-Driven Variable Decomposition
Kun Kuang, Peng Cui, Bo Li, Meng Jiang, Shiqiang Yang, Fei 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 confounder/adjustment-variable separation (orthogonality regularizer, mu>0) (ablation) | D2VD · Synthetic T_missp, m=1000, n=50 | ATE bias: 0.269 -> 0.066 | Improved |
| add variable separation (ablation) | D2VD · Synthetic T_missp, m=1000, n=50 | ATE SD: 0.162 -> 0.113 | Improved |
| add variable separation (ablation) | D2VD · Synthetic T_logit, m=1000, n=50 | ATE bias: 0.053 -> 0.045 | Improved |
| add variable separation (ablation) | D2VD · Synthetic T_logit, m=1000, n=200 | ATE bias: 0.018 -> 0.067 | Hurt |
| use D2VD joint estimator instead of sequential doubly robust | ATE estimation · Synthetic T_missp, m=1000, n=50 | ATE bias: 0.138 -> 0.066 | Improved |
| use D2VD instead of IPW with lasso | ATE estimation · Synthetic T_missp, m=5000, n=200 | ATE bias: 0.142 -> 0.032 | Improved |
| use D2VD instead of IPW | ATE estimation · WeChat ads, With Delicacy Plugin | ATE vs matching reference: -0.253 -> 0.124 (matching 0.099) | Improved |
Closest papers by meaning
- An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation (NeurIPS 2025 · similarity 0.88)
- Automating the Selection of Proxy Variables of Unmeasured Confounders (ICML 2024 · similarity 0.87)
- Doubly robust identification of treatment effects from multiple environments (ICLR 2025 · similarity 0.86)
- Data Fusion for Partial Identification of Causal Effects (NeurIPS 2025 · similarity 0.86)
- Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder (ICLR 2024 · similarity 0.85)
- Conditional Instrumental Variable Regression with Representation Learning for Causal Inference (ICLR 2024 · 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.
