AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Matching without Group Barrier for Heterogeneous Treatment Effect Estimation

Yuguang Yan, Haolin Yang, Shihao Zhang, Weilin Chen, Ruichu Cai, Zhifeng Hao

ICLR 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Meta-learners and partial identification

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
allow neighbors from all treatment groups instead of only the target group (ablation)MOGA matching · News-4sqrt(PEHE): 8.0039 -> 5.9601Improved
allow neighbors from all groups instead of target group only (ablation)MOGA matching · News-4eATE: 2.9041 -> 1.1551Improved
learn distance from factual outcomes via optimal transport instead of squared Euclidean (ablation)MOGA · TCGAsqrt(PEHE): 12.5989 -> 10.5965Improved
learn distance from factual outcomes instead of cosine distance (ablation)MOGA · TCGAeATE: 4.1404 -> 2.7850Improved
joint distance learning instead of two-stage learning (ablation)MOGA · News-2sqrt(PEHE): 5.218 -> 5.081Improved
joint distance learning instead of two-stage learning (ablation)MOGA · News-4AMSE: 5.968 -> 4.420Improved
use MOGA instead of GOMmatching estimator · News-2sqrt(PEHE): 6.451 -> 5.081Improved
use MOGA instead of MitNetHTE estimator · News-8sqrt(mPEHE): 9.282 -> 8.904Improved
use MOGA instead of GOMmatching estimator · TCGAsqrt(mPEHE): 10.545 -> 10.597No clear effect
use MOGA instead of MitNet under stronger confoundingHTE estimator · Synthetic m=[0.1,0.5,0.9,1.3,1.7]sqrt(PEHE): 1.388 -> 1.376Improved
use MOGA instead of kNNmatching estimator · LalondeMAE: 275.2712 -> 246.1526Improved
use MOGA instead of PSMmatching estimator · News-2sqrt(PEHE): 14.957 -> 5.081Improved

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