AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes

Zhaozhi Qian, Yao Zhang, Ioana Bica, Angela Mary Wood, Mihaela van der Schaar

NeurIPS 2021 · Probabilistic and scientific modeling › Treatment effects · approach: Meta-learners and partial identification · 10 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
train representation with both reconstruction and supervised losses instead of reconstruction only (ablation)SyncTwin · Simulated statin LDL, N0=1000, p0=0.1ITE MAE: 0.256 -> 0.178Improved
add reconstruction loss to supervised-only training (ablation)SyncTwin · Simulated statin LDL, N0=200, p0=0.5ITE MAE: 0.119 -> 0.128Mixed
use latent-factor synthetic twin instead of CFRNet-style predictionSyncTwin · Simulated statin LDL, N0=200, p0=0.1ITE MAE: 0.903 -> 0.323Improved
use SyncTwin instead of CRN/RMSN on real CPRD dataSyncTwin · CPRD LDL vs HPS RCTestimated ATE on LDL (mmol/L): -0.72 / -0.83 -> -1.25 (RCT -1.26)Improved

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