Research map / Probabilistic and scientific modeling / Treatment effects
Instrumental Variable Regression with Confounder Balancing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 balancing (Wasserstein IPM on representation) to IV regression (CB-IV vs OneSIV/DFIV) | IV regression · Syn-2-4-4 binary treatment | ATE bias: 0.016 vs 0.661 (OneSIV) | Helped |
| Confounder balancing with IV (CB-IV) vs confounder-balancing-only baseline DRCFR | binary treatment synthetic data · Syn-2-4-4 | ATE bias: 0.016 vs 0.136 | Helped |
| Add IV regression with confounder balancing on IHDP with unmeasured confounders | CB-IV · IHDP-2-4-2 | ATE bias: 0.160 vs 0.434 (DRCFR) | Helped |
| Balanced IV regression (CB-IV) on Demand continuous treatment data | continuous treatment · Demand-0-1 | MSE: 165.0 vs 195.2 (DFIV) | Helped |
| Confounder balancing in IV regression on Demand data with amplified confounding | continuous treatment · Demand-0-5 | MSE: 234.1 vs 465.3 (CFR) | Helped |
| Balancing-only methods (no IV) on Demand-5-1 when only instrument information increases | confounder balancing without IV · Demand-5-1 | MSE: 440.1 (DirectRep), 449.6 (CFR) vs ~191 on Demand-0-1 | Hurt |
| Balanced confounder representation on IHDP with unmeasured confounders relative to IHDP without | confounder balancing baselines (DRCFR, CFR) · IHDP-2-4-2 vs IHDP-2-6-0 | ATE bias: DRCFR 0.055 -> 0.434 | Hurt |
Closest papers by meaning
- Conditional Instrumental Variable Regression with Representation Learning for Causal Inference (ICLR 2024 · similarity 0.89)
- Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data (NeurIPS 2024 · similarity 0.87)
- Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models (ICML 2025 · similarity 0.86)
- An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation (NeurIPS 2025 · similarity 0.85)
- Automating the Selection of Proxy Variables of Unmeasured Confounders (ICML 2024 · similarity 0.84)
- Doubly robust identification of treatment effects from multiple environments (ICLR 2025 · similarity 0.84)
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.