Data-driven rank breaking for efficient rank aggregation

MaRDI QIDQ2834539zbMATH OpenFDO

Authors Ashish Khetan, Sewoong Oh

Publication date 22 November 2016

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1601.05495, http://jmlr.csail.mit.edu/papers/v17/16-209.html

zbMATH Keywords

Plackett-Luce modelrank aggregationsample complexity

Mathematics Subject Classification ID

Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50) Statistical ranking and selection procedures (62F07) Decision theory (91B06)

Recommendations

• Generalized rank-breaking: computational and statistical tradeoffs
• Rank Centrality: Ranking from Pairwise Comparisons
• Collaborative Ranking: An Aggregation Algorithm for Individuals’ Preference Estimation
• Simple, Robust and Optimal Ranking from Pairwise Comparisons
• Ranking recovery from limited pairwise comparisons using low-rank matrix completion

Cited in

(9)

• Stagewise learning for noisy \(k\)-ary preferences
• Worst-case versus average-case design for estimation from partial pairwise comparisons
• Space oriented rank-based data integration
• Generalized rank-breaking: computational and statistical tradeoffs
• Learning from comparisons and choices
• Collaborative Ranking: An Aggregation Algorithm for Individuals’ Preference Estimation
• Developing a ranking problem library (RPLIB) from a data-oriented perspective
• Approximate maximum rank aggregation: beyond the worst-case
• PAC battling bandits in the Plackett-Luce model

This page was built for publication: Data-driven rank breaking for efficient rank aggregation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2834539)