AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Augmented Transfer Regression Learning with Semi-non-parametric Nuisance Models

Molei Liu, Yi Zhang, Katherine P. Liao, Tianxi Cai

JMLR 2023 · 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
use semi-non-parametric nuisance models instead of parametric onesdoubly robust transfer estimator · Simulation (i), nonlinear effectsaverage RMSE: 0.141 -> 0.123Improved
use semi-non-parametric nuisance models instead of parametric onesdoubly robust transfer estimator · Simulation (iii), nonlinear effectsaverage RMSE: 0.207 -> 0.134Improved
use semi-non-parametric nuisance models instead of parametric onesdoubly robust transfer estimator · Simulation (i)average absolute bias: 0.065 -> 0.030Improved
use semi-non-parametric nuisance models instead of parametric onesdoubly robust transfer estimator · Simulation (iii)average absolute bias: 0.092 -> 0.019Improved
add redundant nonparametric component when parametric model is correctATReL · Simulation (ii)average RMSE: 0.117 -> 0.123No clear effect
add redundant nonparametric component when parametric model is correctATReL · Simulation (iv)average RMSE: 0.131 -> 0.122No clear effect
use ATReL instead of DML with basis expansionsdoubly robust transfer estimator · Simulation (i)average RMSE: 0.179 -> 0.123Improved
use ATReL instead of DML with kernel machinedoubly robust transfer estimator · Simulation (iii)average absolute bias: 0.062 -> 0.019Improved
use ATReL instead of DML with basis expansionsdoubly robust transfer estimator · Simulation (iv)deviance of coverage probability: 0.22 -> 0.02Improved
use ATReL instead of Source estimator without covariate shift correctionRA phenotyping · RA EHR phenotyping 2016RMSPE: 0.052 -> 0.011Improved
use ATReL instead of parametric doubly robust estimatorRA phenotyping · RA EHR phenotyping 2016RMSPE: 0.048 -> 0.011Improved
use ATReL instead of DML with kernel machineRA phenotyping · RA EHR phenotyping 2016false classification rate vs gold standard: 0.030 -> 0.010Improved

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