B1263
Title: Multi-task Gaussian processes models for functional data and application to the prediction of swimming performances
Authors: Arthur Leroy - University of Sheffield (United Kingdom) [presenting]
Abstract: Gaussian process regression is a common tool of supervised learning that provides a convenient probabilistic framework, leading to predictions with proper uncertainty quantification. However, the learning procedure in such models generally focuses on hyper-parameters estimation of the covariance structure rather than the prior mean of the process. Therefore, prediction quality might severely decrease with an inappropriate prior mean as we move away from observation points. A multi-task extension of the GP framework is introduced, where data are supposed to come from several individuals sharing some structure altogether. This approach offers more reliable predictions even when a new individual is observed on a few or sparse input locations. Then, the model is enhanced with a clustering component to provide cluster-specific GP predictions. We handle talent identification in sports, and illustrate the approach with this application involving performance swimming datasets. We will see how the proposed algorithm provides reliable probabilistic predictions of future performances while simultaneously allocating swimmers into clusters of similar individuals.
