Abstract
In applications such as rank aggregation, mixture models for permutations are frequently used when the population exhibits heterogeneity. In this work, we study the widely used Mallows mixture model. In the high-dimensional setting, we propose a polynomial-time algorithm that learns a Mallows mixture of permutations on n elements with the optimal sample complexity that is proportional to , improving upon previous results that scale polynomially with n. In the high-noise regime, we characterize the optimal dependency of the sample complexity on the noise parameter. Both objectives are accomplished by first studying demixing permutations under a noiseless query model using groups of pairwise comparisons, which can be viewed as moments of the mixing distribution, and then extending these results to the noisy Mallows model by simulating the noiseless oracle.
Funding Statement
C.M. was supported in part by the NSF Grant DMS-2053333. Y.W. was supported in part by the NSF Grant CCF-1900507, the NSF CAREER award CCF-1651588, and an Alfred Sloan fellowship.
Acknowledgements
The authors thank the anonymous reviewers for their helpful comments.
Citation
Cheng Mao. Yihong Wu. "Learning mixtures of permutations: Groups of pairwise comparisons and combinatorial method of moments." Ann. Statist. 50 (4) 2231 - 2255, August 2022. https://doi.org/10.1214/22-AOS2185
Information