AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Non-parametric Quantile Regression via the K-NN Fused Lasso

Steven Siwei Ye, Oscar Hernan Madrid Padilla

JMLR 2021 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 11 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 quantile K-NN fused lasso instead of quantile random forest under Cauchy errorsScenario 1, Cauchy errors, n=10000 · SimulationMSE: 57748.95 -> 0.0962Improved
use quantile K-NN fused lasso instead of K-NN fused lasso under Cauchy errorsScenario 1, Cauchy errors, n=10000 · SimulationMSE: 4799.0 -> 0.0962Improved
use quantile K-NN fused lasso instead of K-NN fused lasso under Gaussian errorsScenario 1, N(0,1), n=10000 · SimulationMSE: 0.0292 -> 0.0370Hurt
use quantile K-NN fused lasso instead of quantile random forest on Scenario 3 (t2 errors)Scenario 3, n=10000 · SimulationMSE: 1.2910 -> 0.0059Improved
use quantile K-NN fused lasso instead of K-NN fused lasso on Scenario 2 (t3 errors)Scenario 2, n=10000 · SimulationMSE: 0.0542 -> 0.0265Improved
use quantile K-NN fused lasso instead of quantile random forest at small sample size, Scenario 4 tau=0.9Scenario 4, n=100 · SimulationMSE: 0.6948 -> 0.7413Hurt
use quantile K-NN fused lasso instead of quantile random forest at larger sample size, Scenario 4 tau=0.9Scenario 4, n=1000 · SimulationMSE: 0.5374 -> 0.3568Improved
use quantile K-NN fused lasso instead of quantile random forest for medianCalifornia housing, train size 10000 · California housingMSE: 0.1623 -> 0.1479Improved
use quantile K-NN fused lasso instead of quantile random forest for 95% interval coverageCalifornia housing, train size 10000 · California housingcoverage proportion: 0.8902 -> 0.9274Improved
use quantile K-NN fused lasso instead of quantile random forest for median, small training sizeChicago crime, train size 500 · Chicago crimeMSE: 1.1441 -> 1.2161Hurt
use quantile K-NN fused lasso instead of quantile random forest for median, large training sizeChicago crime, train size 2000 · Chicago crimeMSE: 0.8383 -> 0.8476No clear effect
use majorize-minimize instead of linear programming or ADMM solverquantile K-NN fused lasso · Scenario 3 timingcomputation timeImproved

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