English

Maximum Selection and Ranking under Noisy Comparisons

Machine Learning 2017-05-16 v1

Abstract

We consider (ϵ,δ)(\epsilon,\delta)-PAC maximum-selection and ranking for general probabilistic models whose comparisons probabilities satisfy strong stochastic transitivity and stochastic triangle inequality. Modifying the popular knockout tournament, we propose a maximum-selection algorithm that uses O(nϵ2log1δ)\mathcal{O}\left(\frac{n}{\epsilon^2}\log \frac{1}{\delta}\right) comparisons, a number tight up to a constant factor. We then derive a general framework that improves the performance of many ranking algorithms, and combine it with merge sort and binary search to obtain a ranking algorithm that uses O(nlogn(loglogn)3ϵ2)\mathcal{O}\left(\frac{n\log n (\log \log n)^3}{\epsilon^2}\right) comparisons for any δ1n\delta\ge\frac1n, a number optimal up to a (loglogn)3(\log \log n)^3 factor.

Keywords

Cite

@article{arxiv.1705.05366,
  title  = {Maximum Selection and Ranking under Noisy Comparisons},
  author = {Moein Falahatgar and Alon Orlitsky and Venkatadheeraj Pichapati and Ananda Theertha Suresh},
  journal= {arXiv preprint arXiv:1705.05366},
  year   = {2017}
}
R2 v1 2026-06-22T19:47:38.146Z