AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

On The Structure of Parametric Tournaments with Application to Ranking from Pairwise Comparisons

Vishnu Veerathu, Arun Rajkumar

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of ranking and selection · 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
use PairwiseBlockRank instead of MC + CopelandMC + Copeland · DOTAupset ratio: 0.311 ±0.01 -> 0.23 ±0.03Improved
use PairwiseBlockRank instead of Rank CentralityRank Centrality · Tennisupset ratio: 0.285 ±0.008 -> 0.281 ±0.006Improved
use PairwiseBlockRank instead of Rank CentralityRank Centrality · DOTAupset ratio: 0.215 ±0.01 -> 0.23 ±0.03No clear effect
use PairwiseBlockRank instead of MC + CopelandMC + Copeland · Jesterupset ratio: 0.05 ±0.001 -> 0.05 ±0.001No clear effect
use PairwiseBlockRank instead of Blade-ChestBlade-Chest · Jesterupset ratio: 0.15 ±0.022 -> 0.05 ±0.001Improved
increase number of comparisons K per pair on synthetic local-global dataMC + PairwiseBlockRank · Synthetic, n=600, 3 blockspairwise disagreementsImproved
increase known fraction beta of compared pairsMC + PairwiseBlockRank · Synthetic, n=600, 3 blockspairwise disagreementsImproved
increase K for Rank Centrality and other baselinesRank Centrality · Synthetic, n=600, 3 blockspairwise disagreementsNo 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