Achievability and Impossibility of Exact Pairwise Ranking
Abstract
We consider the problem of recovering the rank of a set of $n$ items based on noisy pairwise comparisons. We assume the SST class as the family of generative models. Our analysis gave sharp information theoretic upper and lower bound for the exact requirement, which matches exactly in the parametric limit. Our tight analysis on the algorithm induced by the moment method gave better constant in Minimax optimal rate than ~\citet{shah2017simple} and contribute to their open problem. The strategy we used in this work to obtain information theoretic bounds is based on combinatorial arguments and is of independent interest.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2021
- DOI:
- 10.48550/arXiv.2111.10021
- arXiv:
- arXiv:2111.10021
- Bibcode:
- 2021arXiv211110021H
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Machine Learning