On the rate of convergence of a classifier based on a transformer encoder

Department of Computer Engineering2024-11-0920220018-944810.1109/tit.2022.31917472-s2.0-85135219411https://hdl.handle.net/20.500.14288/3526Pattern recognition based on a high-dimensional predictor is considered. A classifier is defined which is based on a Transformer encoder. The rate of convergence of the misclassification probability of the classifier towards the optimal misclassification probability is analyzed. It is shown that this classifier is able to circumvent the curse of dimensionality provided the a posteriori probability satisfies a suitable hierarchical composition model. Furthermore, the difference between the Transformer classifiers theoretically analyzed in this paper and the ones used in practice today is illustrated by means of classification problems in natural language processing.pdfComputer scienceEngineeringInformation systemsOn the rate of convergence of a classifier based on a transformer encoderJournal Article1557-9654https://doi.org/10.1109/tit.2022.3191747891796100027Q3NOIR03951