AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

ReLU Regression with Massart Noise

Ilias Diakonikolas, Jongho Park, Christos Tzamos

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Coresets and sublinear estimation · 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
add radial-isotropic transformation to l1 regressionl1 regression · Synthetic linear, eta varied, 120 samplesexact recovery rateImproved
add radial-isotropic transformation to l1 regressionl1 regression · Synthetic linear, eta=0.25, sample size variedexact recovery rateImproved
add normalization preprocessing to l1 regressionl1 regression · Synthetic linear mixture of Gaussiansexact recovery rateNo clear effect
add isotropic transformation preprocessing to l1 regressionl1 regression · Synthetic linearexact recovery rateNo clear effect
apply radial-isotropic transformation inside gradient descent on l1 lossgradient descent · Synthetic ReLU, eta=0.4, 240 samplesl2 distance to optimumImproved
apply isotropic transformation inside gradient descent on l1 lossgradient descent · Synthetic ReLU, eta=0.4l2 distance to optimumMixed
use Rescaled L1 instead of naive l1 regression at minimal noisel1 regression · Drug discovery datasetfraction of test points within marginHurt
use Rescaled L1 instead of baselines at moderate to high noisel1 regression, least squares, ridge · Drug discovery datasetfraction of test points within marginImproved

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