AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Statistical Inference for High-dimensional Partially Linear Models via Debiased Rank Lasso

Songshan Yang, Delin Zhao, Runze Li

JMLR 2026 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling

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 data-split rank Lasso instead of two-step projection Lasso under Cauchy errorspartially linear model estimator · Simulation Ex.1, Cauchy, N=450l1 error: 5.185 -> 1.907Improved
use data-split rank Lasso instead of two-step Lasso under t(2) errorspartially linear model estimator · Simulation Ex.1, t(2), N=450l1 error: 1.710 -> 1.051Improved
use data-split rank Lasso instead of two-step Lasso under log-normal errorspartially linear model estimator · Simulation Ex.1, LogN, N=450l1 error: 0.928 -> 0.610Improved
use data-split rank Lasso instead of two-step Lasso under normal errorspartially linear model estimator · Simulation Ex.1, N(0,2^2), N=450l1 error: 0.926 -> 0.976No clear effect
use data-split rank Lasso to reduce false positivespartially linear model estimator · Simulation Ex.1, N(0,2^2), N=450false positives: 11.46 -> 0.200Improved
use data-split rank Lasso to avoid false negatives under Cauchy errorspartially linear model estimator · Simulation Ex.1, Cauchy, N=450false negatives: 1.680 -> 0.010Improved
use ANOPE subsampled loss instead of full pairwise rank loss (ablation)DSRLasso · Simulation Ex.1, Cauchy, N=450l1 error: 1.907 -> 1.943No clear effect
use debiased DSRLasso instead of debiased TSLasso for CI length under Cauchy errorsdebiased estimator · Simulation Ex.2, Cauchy, N=450average CI length (active set): 12.90 -> 1.104Improved
use debiased DSRLasso instead of debiased TSLasso for power under Cauchy errorsdebiased estimator · Simulation Ex.2, Cauchy, N=450power (ARPB): 0.438 -> 0.992Improved
use debiased DSRLasso instead of debiased TSLasso for simultaneous CI length under Cauchy errorsdebiased estimator · Simulation Ex.3 NST, Cauchy, N=450average simultaneous CI length: 26.01 -> 2.868Improved
use debiased DSRLasso instead of debiased TSLasso for simultaneous test power under Cauchy errorsdebiased estimator · Simulation Ex.3 NST, Cauchy, N=450rejection probability: 0.320 -> 0.985Improved
use debiased DSRLasso instead of debiased TSLasso for coverage under normal errorsdebiased estimator · Simulation Ex.2, N(0,2^2), N=300coverage of beta_1 (CP1): 0.870 -> 0.915Improved

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