Loading...
Improving the Scalability of Neural Network Surface Code Decoders
Wu, Kevin Yipu
Wu, Kevin Yipu
Abstract
Quantum computers have recently gained significant recognition due to their ability to solve problems intractable to classical computers. However, due to difficulties in building actual quantum computers, they have large error rates. Thus, advancements in quantum error correction are urgently needed to improve both their reliability and scalability. Here, we first present a type of topological quantum error correction code called the surface code, and we discuss recent developments and challenges of creating neural network decoders for surface codes. In particular, the amount of training data needed to reach the performance of algorithmic decoders grows exponentially with the size of the quantum code, greatly limiting the applicability of this type of decoder. Here, we propose two approaches to this problem: the convolutional decoder and the transformer decoder. Using dimension reduction techniques, we can decrease the dependency on large data sets and accelerate the training process. Our results demonstrate that the compression performed by the convolutional decoder may lessen data dependence and that the compression performed by the transformer decoder may accelerate training, which leads to promising directions for future work.
Description
Date
2024-05-01
Journal Title
Journal ISSN
Volume Title
Publisher
Collections
Download Dataset
Rights Holder
Usage License
Embargo
Research Projects
Organizational Units
Journal Issue
Keywords
Citation
Advisor
Li, Qun
Li, Chi-Kwong
Mao, Weizhen
Li, Chi-Kwong
Mao, Weizhen
Department
Computer Science