On Estimation in Tournaments and Graphs under Monotonicity Constraints

TL;DR

This paper introduces a computationally efficient estimator for probability matrices in tournaments and graphs under monotonicity constraints, providing asymptotic risk bounds and adaptation properties for various models.

Contribution

It proposes a natural, tractable estimator that avoids exhaustive permutation searches and establishes its theoretical performance and adaptability across multiple models.

Findings

Estimator achieves asymptotic risk bounds.

Automatic adaptation to various subclasses.

Applicable to models like Bradley Terry, Beta, and Stochastic Block.

Abstract

We consider the problem of estimating the probability matrix governing a tournament or linkage in graphs from incomplete observations, under the assumption that the probability matrix satisfies natural monotonicity constraints after being permuted in both rows and columns by some latent permutation. This condition is classical in the social sciences literature (see Fishburn(1973)) and has been studied in the statistics literature in recent work (see Chatterjee (2015) and Shah et al. (2016)). In this paper, we investigate in detail a natural estimator which bypasses the need to search over all possible latent permutations and hence is computationally tractable, and derive asymptotic risk bounds for our estimator. In addition, we prove an automatic adaptation property of our estimator for several sub classes of our parameter space which are of natural interest. These sub classes include generalizations of the popular Bradley Terry Model in the Tournament case, the Beta model and Stochastic Block Model in the Graph case, and Holder smooth matrices in the tournament and graph settings.