AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence

Nihar B. Shah, Sivaraman Balakrishnan, Joseph Bradley, Abhay Parekh, Kannan Ramchandran, Martin J. Wainwright

JMLR 2016 · Learning theory and algorithms › Sample complexity · approach: Computational thresholds in graphs and structure · 90 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
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Circle taskerror: 17% -> 6%Improved
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Age taskerror: 17% -> 13%Improved
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Tagline taskerror: 42% -> 44%No clear effect
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Spelling taskerror: 42% -> 40%Improved
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Distance taskerror: 20% -> 17%Improved
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Audio taskerror: 29% -> 20%Improved
elicit ordinal comparisons directly instead of converting cardinal ratingsMTurk crowdsourcing · Relevance taskerror: 35% -> 31%Improved
elicit ordinal comparisons instead of cardinal ratingsMTurk crowdsourcing · Spelling taskmedian completion time: 525s -> 316sImproved
elicit ordinal comparisons instead of cardinal ratingsMTurk crowdsourcing · Audio taskmedian completion time: 134s -> 66sImproved
elicit ordinal comparisons instead of cardinal ratingsMTurk crowdsourcing · Tagline taskmedian completion time: 342s -> 251sImproved
use ordinal Thurstone MLE rather than cardinal MLE with multiple workersMTurk crowdsourcing · Distance tasknormalized squared error: 0.330 -> 0.168Improved
use ordinal Thurstone MLE rather than cardinal MLE with multiple workersMTurk crowdsourcing · Spelling tasknormalized squared error: 0.350 -> 0.358No 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