AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Coresets for Classification – Simplified and Strengthened

Tung Mai, Cameron N Musco, Anup Rao

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Learning halfspaces under noise · 9 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
sample by l1 Lewis weights instead of uniform samplingcoreset for logistic/hinge loss · Webb Spam, Covertype, KDD Cup '99relative loss vs coreset sizeImproved
sample by l1 Lewis weights instead of sqrt leverage scorescoreset for logistic/hinge loss · KDD Cup '99 (mu_y=35.18)relative loss vs coreset sizeImproved
sample by l1 Lewis weights instead of sqrt leverage scorescoreset for logistic/hinge loss · Covertype and Webb Spamrelative loss vs coreset sizeNo clear effect
add L2 regularizationuniform sampling coreset · Covertype and Webb Spamrelative loss at small coreset sizesImproved
use Lewis weights instead of leverage-score-based sampling in theorycoreset size bound · logistic and hinge lossnumber of samples: O~(d^3 mu^3/eps^4) -> O~(d mu^2/eps^2)Improved

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