QLunch: Matthias Caro

Speaker: Matthias Caro from the Technical University of Munich

Title: Generalization in quantum machine learning from few training data

Abstract: 

Modern quantum machine learning (QML) methods involve variationally optimizing a parameterized quantum circuit on a training data set, and subsequently making predictions on a testing data set (i.e., generalizing). In this talk, I will give an introduction to variational QML and to statistical learning theory, and then show guarantees on the generalization performance in variational QML after training on a limited number of training data points.
This talk is based on arXiv:2111.05292.