AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification

Hyun-Suk Lee, Yao Zhang, William Zame, Cong Shen, Jang-Won Lee, Mihaela van der Schaar

NeurIPS 2020 · Probabilistic and scientific modeling › Treatment effects · approach: Benchmarking treatment effect models · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · Synthetic dataset AV^in: 0.04$\pm$.01 -> 0.03$\pm$.001Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · Synthetic dataset ACI width: 3.96$\pm$.16 -> 0.08$\pm$.003Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · Synthetic dataset BV^across: 2.24$\pm$.06 -> 2.39$\pm$.04Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · Synthetic dataset BV^in: 0.30$\pm$.05 -> 0.12$\pm$.01Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · Synthetic dataset BCI width: 2.77$\pm$.20 -> 0.88$\pm$.06Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · IHDPV^across: 0.31$\pm$.04 -> 0.46$\pm$.04Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · IHDPV^in: 0.57$\pm$.05 -> 0.38$\pm$.03Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · IHDPCI width: 3.71$\pm$.08 -> 1.27$\pm$.22Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · CPPV^across: 0.03$\pm$.01 -> 0.06$\pm$.02Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · CPPV^in: 0.12$\pm$.01 -> 0.10$\pm$.01Improved
Use confident-homogeneity partitioning instead of CT-A partitioningR2P-HTE vs CT-A · CPPCI width: 2.45$\pm$.06 -> 1.11$\pm$.13Improved
Use a less accurate ITE estimator (Dragonnet instead of CMGP) (ablation)R2P-HTE · Synthetic dataset BV^in: 0.12$\pm$.01 -> 0.19$\pm$.03Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy