The reviewed record of science sign in
Pith

arxiv: 2111.14574 · v1 · pith:2B5R6QW7 · submitted 2021-11-29 · math.ST · cs.LG· stat.TH

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

Reviewed by Pithpith:2B5R6QW7open to challenge →

classification math.ST cs.LGstat.TH
keywords classifiertransformerprobabilityanalyzedclassifiersconvergenceencodermisclassification
0
0 comments X
read the original abstract

Pattern 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 aposteriori probability satisfies a suitable hierarchical composition model. Furthermore, the difference between Transformer classifiers analyzed theoretically in this paper and Transformer classifiers used nowadays in practice are illustrated by considering classification problems in natural language processing.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.