Active ranking from pairwise comparisons and when parametric assumptions do not help

DOI10.1214/18-AOS1772zbMath1435.62293arXiv1606.08842MaRDI QIDQ2284367

Kannan Ramchandran, Nihar B. Shah, Reinhard Heckel, Martin J. Wainwright

Publication date: 15 January 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1606.08842

zbMATH Keywords

rankingonline learningpairwise comparisonsactive learningmulti-armed banditsBradley-Terry-Luce model

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Paired and multiple comparisons; multiple testing (62J15)

Related Items (11)

Low Permutation-rank Matrices: Structural Properties and Noisy Completion ⋮ Robust Learning of Consumer Preferences ⋮ Ranking and selection for pairwise comparison ⋮ Unnamed Item ⋮ A General Pairwise Comparison Model for Extremely Sparse Networks ⋮ Towards optimal estimation of bivariate isotonic matrices with unknown permutations ⋮ Active ranking from pairwise comparisons and when parametric assumptions do not help ⋮ Spectral method and regularized MLE are both optimal for top-\(K\) ranking ⋮ Unnamed Item ⋮ Time-homogeneous top-K ranking using tensor decompositions ⋮ Asymptotically Optimal Sequential Design for Rank Aggregation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The \(K\)-armed dueling bandits problem
• MM algorithms for generalized Bradley-Terry models.
• Active ranking from pairwise comparisons and when parametric assumptions do not help
• Majorization, entropy and paired comparisons
• Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence
• Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues
• Simple, Robust and Optimal Ranking from Pairwise Comparisons
• Competitive analysis of the top-K ranking problem
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• A Sequential Procedure for Selecting the Population with the Largest Mean from $k$ Normal Populations

This page was built for publication: Active ranking from pairwise comparisons and when parametric assumptions do not help