AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Decorrelated Local Linear Estimator: Inference for Non-linear Effects in High-dimensional Additive Models

Zijian Guo, Wei Yuan, Cunhui Zhang

JMLR 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Distributional treatment effects

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
add decorrelation bias correction (DLL instead of plug-in) (ablation)local linear estimator · Simulation Setting 2, p=1500bias percentage of RMSE: 0.563 -> 0.133Improved
add decorrelation bias correction (DLL instead of plug-in) (ablation)local linear estimator · Simulation Setting 2, p=1500coverage error: 7.46% -> 1.06%Improved
add decorrelation bias correction (DLL instead of plug-in) (ablation)local linear estimator · Simulation Setting 1, p=1500RMSE ratio to oracle: 1.248 -> 1.152Improved
add decorrelation bias correction under dependent covariates (Setting 3) (ablation)local linear estimator · Simulation Setting 3, p=1500coverage error: 1.94% -> 0.77%Improved
add decorrelation bias correction under heavy-tailed t design (Setting 4) (ablation)local linear estimator · Simulation Setting 4, p=1500coverage error: 6.72% -> 1.15%Improved
use DLL instead of ReSmoothing estimatorDLL · Gregory et al. setting, n=100, p=150, r=0.1bias: 0.78 -> 0.22Improved
use DLL instead of ReSmoothing at larger sample size (n=1000)DLL · Gregory et al. setting, a0=-1coverage: OraRS achieves desired coverage at n=1000No clear effect
replace Lasso treatment model by sparse additive model (DLL-S) under non-linear treatmentDLL · Non-linear treatment model, a0=0.10, n=500bias: 0.31 -> 0.23Improved
replace Lasso treatment model by sparse additive model (DLL-S) under non-linear treatmentDLL · Non-linear treatment model, a0=0.10, n=500coverage: 0.84 -> 0.91Improved
replace Lasso treatment model by sparse additive model (DLL-S) under linear treatmentDLL · Linear treatment model, a0=0.10, n=500bias: 0.18 -> 0.22No clear effect
use DLL instead of SIHR linear-model inference on motif regressionDLL · Motif regression, 666 motifs, n=2587detection of non-linear effects: motifs 53, 138, 199, 586 significant under additive model but not under linear SIHRImproved

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