AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Asymptotic Analysis of Sampling Estimators for Randomized Numerical Linear Algebra Algorithms

Ping Ma, Yongkai Chen, Xinlian Zhang, Xin Xing, Jingyi Ma, Michael W. Mahoney

JMLR 2022 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 38 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 IC sampling probabilities instead of BLEV/SLEV for estimating beta_0RandNLA sampling estimator · Simulated MN and T3 datavariance of estimateImproved
use IC, RL, PL instead of BLEV and SLEV on heavy-tailed T1 dataRandNLA sampling estimator · Simulated T1 data (sample size greater than 200)variance of estimateImproved
mix BLEV with uniform sampling (SLEV)BLEV leverage sampling · Simulated datavariance of estimateImproved
use ICNLEV, RLNLEV, PLNLEV instead of SLEV and BLEV for approximating OLSRandNLA sampling estimator · Simulated LN and T1 datavariance of estimateImproved
use ICNLEV instead of other samplersRandNLA sampling estimator · Flight delay dataset (3,274,894 flights)variance of beta_OLS approximationImproved
use ICNLEV, RLNLEV, PLNLEV instead of SLEV and BLEVRandNLA sampling estimator · YearPredictionMSD dataset (515,345 songs)variance of beta_OLS approximationImproved
use different sampling estimatorsRandNLA sampling estimator · All simulation and real datasetssquared biasNo clear effect

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