A transformer front-end plus NSGA-II circuit search produces compact quantum classifiers that match or beat previous quantum models on Iris, Breast Cancer, MNIST (3 digits), and Heart Disease.
Do Quantum Neural Networks have Simplicity Bias?
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
One hypothesis for the success of deep neural networks (DNNs) is that they are highly expressive, which enables them to be applied to many problems, and they have a strong inductive bias towards solutions that are simple, known as simplicity bias, which allows them to generalise well on unseen data because most real-world data is structured (i.e. simple). In this work, we explore the inductive bias and expressivity of quantum neural networks (QNNs), which gives us a way to compare their performance to those of DNNs. Our results show that it is possible to have simplicity bias with certain QNNs, but we prove that this type of QNN limits the expressivity of the QNN. We also show that it is possible to have QNNs with high expressivity, but they either have no inductive bias or a poor inductive bias and result in a worse generalisation performance compared to DNNs. We demonstrate that an artificial (restricted) inductive bias can be produced by intentionally restricting the expressivity of a QNN. Our results suggest a bias-expressivity tradeoff. Our conclusion is that the QNNs we studied can not generally offer an advantage over DNNs, because these QNNs either have a poor inductive bias or poor expressivity compared to DNNs.
citation-role summary
citation-polarity summary
fields
quant-ph 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Genetic Transformer-Assisted Quantum Neural Networks for Optimal Circuit Design
A transformer front-end plus NSGA-II circuit search produces compact quantum classifiers that match or beat previous quantum models on Iris, Breast Cancer, MNIST (3 digits), and Heart Disease.