Gaussian Processes indexed on the symmetric group: prediction and learning
This work addresses ranking problems by providing a novel theoretical framework for Gaussian processes on permutation groups, which is incremental as it adapts existing Euclidean methods to a less studied domain.
The paper tackles the problem of supervised learning for functions defined on permutation groups by extending Gaussian process models to this non-commutative setting, developing harmonic analysis for covariance operators to enable prediction and learning, with applications in statistical ranking.
In the framework of the supervised learning of a real function defined on a space X , the so called Kriging method stands on a real Gaussian field defined on X. The Euclidean case is well known and has been widely studied. In this paper, we explore the less classical case where X is the non commutative finite group of permutations. In this setting, we propose and study an harmonic analysis of the covariance operators that enables to consider Gaussian processes models and forecasting issues. Our theory is motivated by statistical ranking problems.