AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Sharp Oracle Inequalities for Square Root Regularization

Benjamin Stucky, Sara van de Geer

JMLR 2017 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees · 23 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 square root SLOPE instead of square root LASSOsquare root regression · Grouped random beta, theoretical lambdal1 estimation error: 16.90 -> 6.05Improved
use square root SLOPE instead of square root LASSOsquare root regression · Grouped random beta, theoretical lambdal2 prediction error: 66.68 -> 12.84Improved
use square root SLOPE instead of square root LASSOsquare root regression · Decreasing random beta, theoretical lambdal1 estimation error: 8.48 -> 4.50Improved
use square root SLOPE instead of square root LASSOsquare root regression · Decreasing beta, theoretical lambdal1 estimation error: 1.85 -> 2.06Hurt
use square root SLOPE instead of square root LASSOsquare root regression · Decreasing beta, theoretical lambdal2 prediction error: 5.51 -> 4.12Improved
use square root SLOPE instead of square root LASSOsquare root regression · Grouped beta, cross-validated lambdal1 estimation error: 1.83 -> 1.71Improved
use square root SLOPE instead of square root LASSOsquare root regression · Grouped random beta, cross-validated lambdal1 estimation error: 6.14 -> 5.80Improved
use square root SLOPE instead of square root LASSOsquare root regression · Decreasing random beta, cross-validated lambdal1 estimation error: 7.81 -> 7.87Hurt
use cross-validated lambda instead of theoretical lambdasquare root LASSO · Grouped random betal2 prediction error: 66.68 -> 6.67Improved
use randomly placed active set instead of first 7 coordinatesboth estimators · Decreasing betaestimation error: 1.85 -> 8.48Hurt

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