AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

The SKIM-FA Kernel: High-Dimensional Variable Selection and Nonlinear Interaction Discovery in Linear Time

Raj Agrawal, Tamara Broderick

JMLR 2023 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 0 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 SKIM-FA instead of Pairs Lassointeraction variable selection · Synthetic p=1000, Equal setting# wrong covariates selected: 213 -> 0Improved
Use SKIM-FA instead of MARSinteraction variable selection · Synthetic p=1000, Weak Main setting# wrong covariates selected: 75 -> 9Improved
Use SKIM-FA instead of SPAM-2Stageinteraction variable selection · Synthetic p=1000, Weak Main setting# correct covariates selected: 1 -> 5Improved
Use SKIM-FA instead of SPAM-2Stage when main effects are the only signalestimation · Synthetic p=1000, Main Only settingtotal SSE / signal variance: 0.17 -> 0.55Hurt
Use MARS-EMP (re-orthogonalized to empirical measure) instead of MARS-VANILLA (ablation)MARS · Synthetic p=1000, Equal settingtotal SSE / signal variance: 24.64 -> 0.43Improved
Use SKIM-FA instead of MARS-EMPestimation · Synthetic p=1000, Weak Main settingtotal SSE / signal variance: 0.78 -> 0.17Improved
Use SKIM-FA instead of MARSvariable selection · Bike Sharing + 1000 noise covariates# wrong covariates selected: 119 -> 0Improved
Use SKIM-FA instead of MARS-Vanillaestimation · Bike Sharing + 1000 noise covariatestotal SSE: 10.209 -> 0.263Improved
Use SKIM-FA instead of SPAM-2Stage on real dataestimation · Bike Sharing + 1000 noise covariatestotal SSE: 0.269 -> 0.263No clear effect
Use SKIM-FA instead of HierLasso on Main Effects Onlyvariable selection · Synthetic p=1000, Main-Only setting# correct covariates selected: 4 -> 3Hurt

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