A scalable and real-time neural decoder for topological quantum codes

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Senior, Andrew W., Edlich, Thomas, Heras, Francisco J. H., Zhang, Lei M., Higgott, Oscar, Spencer, James S., Applebaum, Taylor, Blackwell, Sam, Ledford, Justin, Žemgulytė, Akvilė, Žídek, Augustin, Shutty, Noah, Cowie, Andrew, Li, Yin, Holland, George, Brooks, Peter, Beattie, Charlie, Newman, Michael, Davies, Alex, Jones, Cody, Boixo, Sergio, Neven, Hartmut, Kohli, Pushmeet, Bausch, Johannes
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917332552515584
author Senior, Andrew W.
Edlich, Thomas
Heras, Francisco J. H.
Zhang, Lei M.
Higgott, Oscar
Spencer, James S.
Applebaum, Taylor
Blackwell, Sam
Ledford, Justin
Žemgulytė, Akvilė
Žídek, Augustin
Shutty, Noah
Cowie, Andrew
Li, Yin
Holland, George
Brooks, Peter
Beattie, Charlie
Newman, Michael
Davies, Alex
Jones, Cody
Boixo, Sergio
Neven, Hartmut
Kohli, Pushmeet
Bausch, Johannes
author_facet Senior, Andrew W.
Edlich, Thomas
Heras, Francisco J. H.
Zhang, Lei M.
Higgott, Oscar
Spencer, James S.
Applebaum, Taylor
Blackwell, Sam
Ledford, Justin
Žemgulytė, Akvilė
Žídek, Augustin
Shutty, Noah
Cowie, Andrew
Li, Yin
Holland, George
Brooks, Peter
Beattie, Charlie
Newman, Michael
Davies, Alex
Jones, Cody
Boixo, Sergio
Neven, Hartmut
Kohli, Pushmeet
Bausch, Johannes
contents Fault-tolerant quantum computing will require error rates far below those achievable with physical qubits. Quantum error correction (QEC) bridges this gap, but depends on decoders being simultaneously fast, accurate, and scalable. This combination of requirements remains unmet by a machine-learning decoder, nor by any decoder for promising resource-efficient codes such as the color code. Here we introduce AlphaQubit 2, a neural-network decoder that achieves near-optimal logical error rates for both surface and color codes at scale under realistic noise. For the color code, it is orders of magnitude faster than other high-accuracy decoders. We demonstrate real-time decoding faster than 1μs per cycle on commercial accelerators: for the surface code to distance 11, with better accuracy than leading real-time decoders; and the first real-time decoding of the color code to distance 9. These results support the practical application of a wider class of promising QEC codes, and establish a credible path towards high-accuracy, real-time neural decoding at the scales required for fault-tolerant quantum computation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07737
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A scalable and real-time neural decoder for topological quantum codes
Senior, Andrew W.
Edlich, Thomas
Heras, Francisco J. H.
Zhang, Lei M.
Higgott, Oscar
Spencer, James S.
Applebaum, Taylor
Blackwell, Sam
Ledford, Justin
Žemgulytė, Akvilė
Žídek, Augustin
Shutty, Noah
Cowie, Andrew
Li, Yin
Holland, George
Brooks, Peter
Beattie, Charlie
Newman, Michael
Davies, Alex
Jones, Cody
Boixo, Sergio
Neven, Hartmut
Kohli, Pushmeet
Bausch, Johannes
Quantum Physics
Machine Learning
81P73, 68T07
I.2.0; J.2
Fault-tolerant quantum computing will require error rates far below those achievable with physical qubits. Quantum error correction (QEC) bridges this gap, but depends on decoders being simultaneously fast, accurate, and scalable. This combination of requirements remains unmet by a machine-learning decoder, nor by any decoder for promising resource-efficient codes such as the color code. Here we introduce AlphaQubit 2, a neural-network decoder that achieves near-optimal logical error rates for both surface and color codes at scale under realistic noise. For the color code, it is orders of magnitude faster than other high-accuracy decoders. We demonstrate real-time decoding faster than 1μs per cycle on commercial accelerators: for the surface code to distance 11, with better accuracy than leading real-time decoders; and the first real-time decoding of the color code to distance 9. These results support the practical application of a wider class of promising QEC codes, and establish a credible path towards high-accuracy, real-time neural decoding at the scales required for fault-tolerant quantum computation.
title A scalable and real-time neural decoder for topological quantum codes
topic Quantum Physics
Machine Learning
81P73, 68T07
I.2.0; J.2
url https://arxiv.org/abs/2512.07737