AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Overlap-weighted orthogonal meta-learner for treatment effect estimation over time

Konstantin Hess, Dennis Frauen, Mihaela van der Schaar, Stefan Feuerriegel

ICLR 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Benchmarking treatment effect models · 1 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 WO-learner instead of best baseline at lowest overlaptransformer meta-learners · D_gamma, gamma=0.5CATE RMSE: 54.4%Improved
use WO-learner instead of best baseline at gamma=1.0transformer meta-learners · D_gamma, gamma=1.0CATE RMSE: 58.4%Improved
use WO-learner instead of best baseline at highest gamma (lowest overlap)transformer meta-learners · D_gamma, gamma=6.5CATE RMSE: 13.5%Improved
use WO-learner instead of best baseline with n_train=5000transformer meta-learners · D_N low-sampleCATE RMSE: 66.9%Improved
use WO-learner instead of best baseline with n_train=2000transformer meta-learners · D_N low-sampleCATE RMSE: 28.7%Improved
use WO-learner instead of best baseline at horizon 4transformer meta-learners · MIMIC-III semi-syntheticCATE RMSE: 28.5%Improved
use WO-learner instead of best baseline at horizon 2transformer meta-learners · MIMIC-III semi-syntheticCATE RMSE: 23.1%Improved
swap transformer backbone for LSTM (ablation)WO-learner · D_gamma, gamma=0.5CATE RMSE: 0.03 -> 0.07Hurt
use WO-learner with LSTM backbone at gamma=1.0 (ablation)WO-learner · D_gamma, gamma=1.0CATE RMSE: -7.8%No clear effect
use WO-learner with LSTM backbone at gamma=1.5 to 6.5 (ablation)LSTM meta-learners · D_gamma, gamma>=1.5CATE RMSE: 46.0% at gamma 1.5; 74.7% at gamma 4.0Improved
add overlap weights and Neyman-orthogonality (WO) versus IPW at gamma=4.0transformer · D_gamma, gamma=4.0CATE RMSE: 0.70 -> 0.10Improved
add Neyman-orthogonal WO relative to RA-learner as covariate dimension growstransformer · D_mu complex responseCATE RMSEImproved

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