AI Paper Atlas

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

Asymptotics for Sketching in Least Squares Regression

Edgar Dobriban, Sifan Liu

NeurIPS 2019 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized sketching for matrices · 24 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 orthogonal Haar projection instead of iid projectionSketch-and-solve least squares · Linear regression, arbitrary X; asymptotic VEVE: VE_iid=VE_Haar+1Improved
Use SRHT instead of iid projectionSketch-and-solve least squares · Linear regression, arbitrary X; asymptotic VEVE: VE_iid=VE_Hadamard+1Improved
Use uniform sampling instead of orthogonal projectionSketch-and-solve least squares · Rotationally invariant XVENo clear effect
Use uniform sampling on non-rotationally-invariant dataSketch-and-solve least squares · Million Song and New York flights datasetsREMixed
Increase projection dimension rSketch-and-solve least squares · Linear regressionVEImproved
Use Gaussian projection even when sample size is not reducedOrdinary least squares · Linear regressionVE: 2Hurt

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