Overfitting in quantum machine learning and entangling dropout

TL;DR

This paper introduces entangling dropout, a technique in quantum machine learning that randomly removes entangling gates during training to reduce overfitting and improve generalization, inspired by classical dropout methods.

Contribution

It proposes a novel quantum analogue of dropout, called entangling dropout, to address overfitting in quantum machine learning models.

Findings

Entangling dropout suppresses overfitting in quantum circuits.

The technique improves generalization in quantum models.

Case studies demonstrate effectiveness of the method.

Abstract

The ultimate goal in machine learning is to construct a model function that has a generalization capability for unseen dataset, based on given training dataset. If the model function has too much expressibility power, then it may overfit to the training data and as a result lose the generalization capability. To avoid such overfitting issue, several techniques have been developed in the classical machine learning regime, and the dropout is one such effective method. This paper proposes a straightforward analogue of this technique in the quantum machine learning regime, the entangling dropout, meaning that some entangling gates in a given parametrized quantum circuit are randomly removed during the training process to reduce the expressibility of the circuit. Some simple case studies are given to show that this technique actually suppresses the overfitting.