AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Stage-Aware Learning for Dynamic Treatments

Hanwen Ye, Wenzhuo Zhou, Ruoqing Zhu, Annie Qu

JMLR 2024 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 5 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 stage-aware partial matching (SAL) instead of IPWE full-matching (BOWL)SAL · Simulation T=10, n=5000, full-matching probability 0.001estimated total reward: 0.347 -> 0.624Improved
Use SAL instead of BOWL at high full-matching probabilitySAL · Simulation T=10, n=5000, full-matching probability 0.100estimated total reward: 0.659 -> 0.686Improved
Decrease sample size from 5000 to 500 (SAL margin over best competitor)SAL · Simulation nonlinear regime, T=5estimated total reward: 10.081% -> 27.924%Improved
Increase number of stages from 5 to 10 (SAL margin over best competitor)SAL · Simulation nonlinear regime, n=5000estimated total reward: 10.081% -> 20.541%Improved
Add stage importance scores to SAL (SWL vs SAL) (ablation)SWL · Simulation nonlinear regime, no important stageestimated total reward: 0.673 -> 0.671No clear effect
Add stage importance scores to SAL when few stages are important (ablation)SWL · Simulation linear homogeneous, n=500, T=10estimated total rewardImproved
Use SWL instead of SAL on ICU 8-stage data (ablation)SWL · UC CORDS ICU, 8 stageshospitalization days: 4.913 -> 6.749Hurt
Use SWL instead of SAL on inpatient 8-stage data (ablation)SWL · UC CORDS Inpatient, 8 stageshospitalization days: 6.704 -> 5.664Improved
Use SWL instead of SAL on ICU 5-stage data (ablation)SWL · UC CORDS ICU, 5 stageshospitalization days: 7.175 -> 5.855Improved
Use SWL instead of BOWL on inpatient 10-stage dataSWL · UC CORDS Inpatient, 10 stageshospitalization days: 15.129 -> 4.817Improved
Linear homogeneous regime: SWL vs BOWL matching accuracy at n=1000SWL · Simulation linear homogeneous, T=5matching accuracy: 74.71% -> 97.36%Improved
Use nonlinear heterogeneous instead of linear homogeneous regime (ablation)SAL/SWL · Simulation, T=5estimated total rewardHurt

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