Learning to Decode in Parallel: Self-Coordinating Neural Network for Real-Time Quantum Error Correction

Abstract

Fast, reliable decoders are pivotal components for enabling fault-tolerant quantum computation. Neural network decoders like AlphaQubit have demonstrated significant potential, achieving higher accuracy than traditional human-designed decoding algorithms. However, existing implementations of neural network decoders lack the parallelism required to decode the syndrome stream generated by a superconducting logical qubit in real time. Moreover, integrating AlphaQubit with sliding window-based parallel decoding schemes presents non-trivial challenges: AlphaQubit is trained solely to output a single bit corresponding to the global logical correction for an entire memory experiment, rather than local physical corrections that can be easily integrated. We address this issue by training a recurrent, transformer-based neural network specifically tailored for parallel window decoding. While our network still outputs a single bit, we derive training labels from a consistent set of local corrections and train on various types of decoding windows simultaneously. This approach enables the network to self-coordinate across neighboring windows, facilitating high-accuracy parallel decoding of arbitrarily long memory experiments.

As a result, we overcome the throughput bottleneck that previously precluded the use of AlphaQubit-type decoders in fault-tolerant quantum computation. Our work presents the first scalable, neural-network-based parallel decoding framework that simultaneously achieves state-of-the-art accuracy and the stringent throughput required for real-time quantum error correction. Using an end-to-end experimental workflow, we benchmark our decoder on the Zuchongzhi 3.2 superconducting quantum processor against existing human-designed decoders on surface codes with distances up to \(7\), demonstrating its superior logical accuracy. Moreover, we demonstrate that, using our approach, a single TPU v6e is capable of decoding surface codes with distances as large as \(25\) within \(1\mu s\) per decoding round.

Recommended citation: Zhang, K., Yi, Z., Guo, S., Kong, L., Wang, S., Zhan, X., ... & Chen, J. (2026). Learning to Decode in Parallel: Self-Coordinating Neural Network for Real-Time Quantum Error Correction. arXiv preprint arXiv:2601.09921.
Download Paper | Download Bibtex