AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging

Rui Wang, Yanyan Ouyang, Panpan Yu, Wangli Xu

NeurIPS 2023 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 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
replace random grouping (VDA) with selected/ordered grouping of observations (ablation)data averaging estimator · Case 2, p=200empirical MSE (x10^3): 1034.62 -> 69.4913Improved
replace random grouping (VDA) with selected grouping (ablation)data averaging estimator · Case 1, p=200empirical MSE (x10^3): 15014 -> 2469.56Improved
replace random grouping (VDA) with selected grouping (ablation)data averaging estimator · Case 4, p=200empirical MSE (x10^3): 345.624 -> 10.658Improved
data averaging into 2p groups instead of IBOSS samplinglinear model sketching · Case 3, p=200empirical MSE (x10^3): 235.444 -> 23.0075Improved
data averaging into 2p groups instead of IBOSS samplinglinear model sketching · Case 4, p=200empirical MSE (x10^3): 37.7542 -> 10.658Improved
data averaging into 2p groups instead of IBOSS samplinglinear model sketching · Case 1, p=50empirical MSE (x10^3): 507.642 -> 182.438Improved
data averaging into 2p groups instead of IBOSS samplinglinear model sketching · Case 4, p=50empirical MSE (x10^3): 2.36205 -> 2.00812Improved
data averaging instead of uniform samplinglinear model sketching · Case 2, p=200empirical MSE (x10^3): 1033.37 -> 69.4913Improved
increase dimension p from 50 to 200 for the proposed methodNEW · Case 1empirical MSE (x10^3): 182.438 -> 2469.56Hurt
use data averaging instead of leverage-score samplinglinear model sketching · Case 5, p=200empirical MSE (x10^3): 1979.68 -> 192.085Improved
use data averaging instead of IBOSS for computing timeNEW · N=8×10^4, p=200 timecomputing time (s): 0.16388 -> 0.21261No clear effect
use data averaging instead of uniform sampling for computing timeNEW · N=8×10^4, p=200 timecomputing time (s): 0.00653 -> 0.21261Hurt

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