Efficient Bayesian Inference for Generalized Bradley-Terry Models

TL;DR

This paper introduces efficient Bayesian inference methods for generalized Bradley-Terry models by reinterpreting existing algorithms as EM algorithms and developing Gibbs samplers, improving computational efficiency across various applications.

Contribution

It reinterprets MM algorithms as EM algorithms with latent variables and develops Gibbs samplers for Bayesian inference in generalized Bradley-Terry models.

Findings

Gibbs samplers outperform MCMC in efficiency

Extensions enable handling of ties and group comparisons

Experimental results show improved computational performance

Abstract

The Bradley-Terry model is a popular approach to describe probabilities of the possible outcomes when elements of a set are repeatedly compared with one another in pairs. It has found many applications including animal behaviour, chess ranking and multiclass classification. Numerous extensions of the basic model have also been proposed in the literature including models with ties, multiple comparisons, group comparisons and random graphs. From a computational point of view, Hunter (2004) has proposed efficient iterative MM (minorization-maximization) algorithms to perform maximum likelihood estimation for these generalized Bradley-Terry models whereas Bayesian inference is typically performed using MCMC (Markov chain Monte Carlo) algorithms based on tailored Metropolis-Hastings (M-H) proposals. We show here that these MM\ algorithms can be reinterpreted as special instances of Expectation-Maximization (EM) algorithms associated to suitable sets of latent variables and propose some original extensions. These latent variables allow us to derive simple Gibbs samplers for Bayesian inference. We demonstrate experimentally the efficiency of these algorithms on a variety of applications.