Research map / Probabilistic and scientific modeling / Treatment effects
Matching on Balanced Nonlinear Representations for Treatment Effects Estimation
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 |
|---|---|---|---|
| Compare BNR-NNM against RNNM, PCA-NNM, LPP-NNM, PSM, Eud/Mah-NNM across dimensions 2-100 | BNR-NNM · Synthetic (N=1000, d=100) | MSE of ATT | Helped |
| Vary matching dimension; best at 5 (ablation) | BNR-NNM · Synthetic | MSE | Mixed |
| Use BNR-NNM instead of RNNM | BNR-NNM · IHDP | epsilon_ATT: 0.16±0.07 -> 0.16±0.06 | No clear effect |
| Use BNR-NNM instead of Eu-NNM | BNR-NNM · IHDP | epsilon_ATT: 0.18±0.06 -> 0.16±0.06 | Helped |
| Use BNR-NNM instead of Mah-NNM | BNR-NNM · IHDP | epsilon_ATT: 0.31±0.12 -> 0.16±0.06 | Helped |
| Use BNR-NNM instead of PCA-NNM | BNR-NNM · IHDP | epsilon_ATT: 0.19±0.11 -> 0.16±0.06 | Helped |
| Use BNR-NNM instead of PSM | BNR-NNM · IHDP | epsilon_ATT: 0.26±0.08 -> 0.16±0.06 | Helped |
| Use BNR-NNM instead of Euclidean NNM | BNR-NNM · LaLonde | ATT bias: 164% -> 12% | Helped |
| Use BNR-NNM instead of PSM | BNR-NNM · LaLonde | ATT bias: 201% -> 12% | Helped |
| Use BNR-NNM instead of RNNM | BNR-NNM · LaLonde | ATT bias: 163% -> 12% | Helped |
| Use BNR-NNM instead of CBPS (balance-aware baseline) | BNR-NNM · LaLonde | ATT bias: 52% -> 12% | Helped |
| Use BNR-NNM instead of DNN counterfactual regression | BNR-NNM · LaLonde | ATT bias: 16% -> 12% | Helped |
Closest papers by meaning
- Adversarially Balanced Representation for Continuous Treatment Effect Estimation (AAAI 2024 · similarity 0.88)
- Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation (ICML 2025 · similarity 0.88)
- Treatment Effects Estimation By Uniform Transformer (ICLR 2024 · similarity 0.87)
- An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series (ICML 2024 · similarity 0.87)
- Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation (AAAI 2024 · similarity 0.87)
- Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing (AAAI 2024 · similarity 0.86)
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.