AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

WOR and $p$'s: Sketches for $\ell_p$-Sampling Without Replacement

Edith Cohen, Rasmus Pagh, David Woodruff

NeurIPS 2020 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 1 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
2-pass WORp instead of perfect WOR samplingWORp · l2, Zipf[2], statistic nu^3NRMSE: 2.09e-11 -> 2.08e-11No clear effect
2-pass WORp instead of perfect WOR samplingWORp · l1, Zipf[1], statistic nu^3NRMSE: 5.73e-03 -> 5.72e-03No clear effect
WOR (2-pass WORp) instead of perfect WR samplingWORp · l2, Zipf[2], statistic nu^3NRMSE: 1.16e-04 -> 2.08e-11Improved
WOR (2-pass WORp) instead of perfect WR samplingWORp · l1, Zipf[1], statistic nu^3NRMSE: 3.59e-01 -> 5.72e-03Improved
WOR (2-pass WORp) instead of perfect WR samplingWORp · l1, Zipf[2], statistic nuNRMSE: 9.51e-03 -> 1.60e-03Improved
WOR (2-pass WORp) instead of perfect WR samplingWORp · l2, Zipf[2], statistic nu^2NRMSE: 7.96e-05 -> 1.25e-07Improved
1-pass WORp (estimated weights) instead of 2-pass WORpWORp · l2, Zipf[2], statistic nu^2NRMSE: 1.25e-07 -> 1.14e-02Hurt
1-pass WORp instead of 2-pass WORpWORp · l1, Zipf[2], statistic nuNRMSE: 1.60e-03 -> 2.79e-02Hurt
1-pass WORp instead of 2-pass WORpWORp · l1, Zipf[1], statistic nu^3NRMSE: 5.72e-03 -> 5.14e-03No clear effect
1-pass WORp instead of perfect WRWORp · l1, Zipf[2], statistic nu^3NRMSE: 3.45e-04 -> 5.11e-05Improved
1-pass WORp instead of perfect WRWORp · l2, Zipf[2], statistic nu^3NRMSE: 1.16e-04 -> 1.06e-03Hurt

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