Comparing Neural Network Based Decoders for the Surface Code
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Matching algorithms can be used for identifying errors in quantum systems, being the most famous the Blossom algorithm. Recent works have shown that small distance quantum error correction codes can be efficiently decoded by employing machine learning techniques based on neural networks (NN). Various NN-based decoders have been proposed to enhance the decoding performance and the decoding time. Their implementation differs in how the decoding is performed, at logical or physical level, as well as in several neural network related parameters. In this work, we implement and compare two NN-based decoders, a low level decoder and a high level decoder, and study how different NN parameters affect their decoding performance and execution time. Crucial parameters such as the size of the training dataset, the structure and the type of the neural network, and the learning rate used during training are discussed. After performing this comparison, we conclude that the high level decoder based on a Recurrent NN shows a better balance between decoding performance and execution time and it is much easier to train. We then test its decoding performance for different code distances, probability datasets and under the depolarizing and circuit error models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Surface codes: Towards practical large-scale quantum computation
Fowler, A. G., Mariantoni, M., Martinis, J. M., & Cleland, A. N. (2012) · Physical Review A · doi:10.1103/physreva.86.032324 · Cited by 3,059 · cited 1×
“The surface code is a topological stabilizer code that has a simple structure, local interactions between qubits and is proven to have high tolerance against errors [7], [20], [22], [23], [24], [25], [26], [27], [28].”
BackgroundEdmonds, J. (1965) · Canadian Journal of Mathematics · doi:10.4153/cjm-1965-045-4 · Cited by 2,428 · cited 1×
“Many classical decoding algorithms have been proposed with themost widely used being the Blossom decoder [6].”
MethodFault-Tolerant Quantum Computation with High Threshold in Two Dimensions
Raussendorf, R., & Harrington, J. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.190504 · Cited by 812
Stabilizer Codes and Quantum Error Correction
Gottesman, D. (1997) · arXiv · doi:10.48550/arxiv.quant-ph/9705052 · Cited by 753
Surface code quantum computing by lattice surgery
Horsman, D., Fowler, A. G., Devitt, S., & Meter, R. V. (2012) · New Journal of Physics · doi:10.1088/1367-2630/14/12/123011 · Cited by 598 · cited 1×
“The smallest surface code created is known as the rotated surface code [30] and it is presented in Fig.”
BackgroundHigh-threshold universal quantum computation on the surface code
Fowler, A. G., Stephens, A. M., & Groszkowski, P. (2009) · Physical Review A · doi:10.1103/physreva.80.052312 · Cited by 486
Quantum codes on a lattice with boundary
Bravyi, S. B., & Kitaev, A. Y. (1998) · arXiv · doi:10.48550/arxiv.quant-ph/9811052 · Cited by 394
Efficient algorithms for maximum likelihood decoding in the surface code
Bravyi, S., Suchara, M., & Vargo, A. (2014) · Physical Review A · doi:10.1103/physreva.90.032326 · Cited by 214 · cited 2×
“For that reason, approximate versions of MLD have been developed like the [34], which reports a running time of Oðnx3Þ, where x is a parameter that controls the approximation precision.”
BackgroundOptimal resources for topological two-dimensional stabilizer codes: Comparative study
Bombin, H., & Martin-Delgado, M. A. (2007) · Physical Review A · doi:10.1103/physreva.76.012305 · Cited by 178 · cited 1×
“Various quantum error correcting codes have been developed so far, but in this work we only consider the surface code [3], [4], [19], [20], [21], one of the most promising QEC codes.”
MethodOptimal complexity correction of correlated errors in the surface code
Fowler, A. G. (2013) · arXiv · doi:10.48550/arxiv.1310.0863 · Cited by 36
Cited by
Learning high-accuracy error decoding for quantum processors
Bausch, J., Senior, A. W., Heras, F. J. H., Edlich, T., Davies, A., Newman, M., Jones, C., Satzinger, K., Niu, M. Y., Blackwell, S., et al. (2024) · Nature · doi:10.1038/s41586-024-08148-8 · Cited by 106
“Training Data Efficiency A concern raised for ML decoders is whether the training data required scales infeasibly with the code distance [95].”
InfluentialDecoding algorithms for surface codes
deMarti iOlius, A., Fuentes, P., Orús, R., Crespo, P. M., & Etxezarreta Martinez, J. (2024) · Quantum · doi:10.22331/q-2024-10-10-1498 · Cited by 60
“The deep neural network decoder proved a better threshold than MWPM at the cost of a higher complexity, while the reinforcement learning decoder proved an almost linear complexity at the cost of a worse code threshold (Varsamopoulos et al., 2020b).”
BackgroundNeural network decoder for near-term surface-code experiments
Varbanov, B. M., Serra-Peralta, M., Byfield, D., & Terhal, B. M. (2025) · Physical Review Research · doi:10.1103/physrevresearch.7.013029 · Cited by 20
Introduction to quantum error correction with stabilizer codes
Bradshaw, Z. P., Dale, J. J., & Evans, E. N. (2026) · Annals of Physics · doi:10.1016/j.aop.2026.170353 · Cited by 4
Metadata
- Authors
- Varsamopoulos, S., Bertels, K., & Almudever, C. G.
- Venue
- IEEE Transactions on Computers
- Published
- 2020-02-01
- Volume
- 69
- Issue
- 2
- Pages
- 300-311
- ISSN
- 0018-9340 (ISSN-L)
- 1557-9956
- 2326-3814
- OpenAlex
- W2981389746
- Cited by
- 76
- References
- 10
- FWCI
- 2.65
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Comparing Neural Network Based Decoders for the Surface Code. https://app.cochat.ai/papers/10.1109/tc.2019.2948612
- The paper
- Varsamopoulos, S., Bertels, K., & Almudever, C. G. (2020). Comparing Neural Network Based Decoders for the Surface Code. IEEE Transactions on Computers. https://doi.org/10.1109/tc.2019.2948612
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.