Quick Navigation
Topics
Quantum Machine Learning
Do Quantum Neural Networks have Simplicity Bias?
arXiv
Authors: Jessica Pointing
Year
2024
Paper ID
65790
Status
Preprint
Abstract Read
~2 min
Abstract Words
206
Citations
N/A
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.
Why This Paper Matters
- This paper contributes to the Quantum Machine Learning research area in the Quantum Articles archive.
- It adds a 2024 reference point for readers tracking recent quantum research.
- 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...
Paper Tools
Become a member to use research tools
Sign in to open papers, visit source links, share, cite, compare, copy DOI links, request category corrections, and build your reading list.
Show Paper arXiv Publisher Share
Cite This Paper
Copy URL
Compare
Copy DOI Add to Reading List
Category Correction Request
Category Correction Request
Help us improve classification quality by proposing a better category. Every request is reviewed by an admin.
Sign in to submit a category correction request for this paper.
Log In to SubmitReferences & Citation Signals
Community Reactions
Quick sentiment from readers on this paper.
Score:
0
Likes: 0
Dislikes: 0
Sign in to react to this paper.
Discussion & Reviews (Moderated)
Average Rating: 0.0 / 5 (0 ratings)
No written reviews yet.