Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2610.40490

Fast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes

Hong-Ye Hu, Zhenlai Wang, Binzhao Luo, Tao Xiang, Chen Zhao

quant-phcs.AIcs.ITcs.LGSubmitted Oct 29, 2026• Announced Oct 30, 2026• 0 citations
arXivHTMLPDF

Abstract

Quantum error correction is essential for fault-tolerant quantum computing. High-rate quantum low-density parity-check (qLDPC) codes have emerged as a promising approach to reducing the substantial physical qubit overhead of quantum error correction, enabling encoding rates exceeding $1/2$ in blocks of approximately one thousand physical data qubits. However, their practical implementation requires decoders that combine high accuracy with low latency to keep pace with quantum hardware. Existing decoders of high-rate qLDPC codes can achieve high accuracy but often incur substantial computational latency, whereas neural network decoders have yet to be demonstrated for high-rate qLDPC codes. Here, we introduce \emph{neural triage decoding}, a framework that uses syndrome consistency to adaptively allocate neural computation. A local neural message-passing network rapidly predicts error corrections, additional iterations reduce residual syndrome violations, and a rarely invoked diversification stage searches for consistent corrections to the remaining shots. We demonstrate that the \texttt{Triage} decoder can decode ultra-high-rate qLDPC codes encoding a few hundred logical qubits, including lifted-product and Kasai codes, achieving state-of-the-art accuracy comparable to the near optimal algorithmic decoders while reducing decoding latency by approximately one to two orders of magnitude. Our framework is inspired by a rigorous analysis of the exact bitwise marginal decoder, revealing a distance-independent syndrome-inconsistent error floor. In addition, we show the robustness of neural network decoders to mismatched error priors. Our results establish adaptive neural decoding as a promising route towards fast, accurate, and scalable quantum error correction in the near term.

AI Summary

The paper addresses whether neural decoders can combine low logical error rates with manageable computational cost for high-rate qLDPC quantum memories. Its **Triage** framework applies a Tanner-graph neural message-passing decoder to the residual syndrome for up to four iterations, then escalates unresolved shots to searches using syndrome flips, prior perturbations and code symmetries. Syndrome-consistent candidates are ranked by likelihood under the original priors. A theoretical analysis shows that exact bitwise MAP decisions can remain syndrome-inconsistent despite using exact marginals. Under specified graph assumptions and independent phenomenological noise, it proves $P_{\mathrm{inc}}=\Omega(p^{\kappa(\nu)})$, where $\kappa(\nu)=\nu/2+1$ for even minimum qubit degree $\nu$ and $\nu+1$ for odd $\nu$. Both benchmark matrices have $\nu=3$, yielding a quartic lower bound at fixed code size. Monte Carlo benchmarks use the $[[1122,148,d\leq20]]$ lifted-product code and $[[1152,580,d\leq12]]$ Kasai code, with five and eight noisy measurement rounds respectively. At $p=1.5\%$, reported per-qubit-per-round logical error rates are $9.33\times10^{-11}$ and $5.08\times10^{-10}$. Full-decoder amortized costs are $2.37$ and $12.3$ ms per shot, versus $815$ and $349$ ms for the selected algorithmic baselines. Networks trained at $p=2\%$ are evaluated across other error rates; separate frontend tests examine robustness to perturbed priors. The timing comparison uses GPU batches of 64 versus CPU baselines, not matched-hardware single-shot latency. Benchmarks use phenomenological noise with perfect final extraction; circuit-level decoding, experimental validation, latency distributions, sustained real-time operation and online calibration remain untested.

Little sign of AI-generated textMissing comparison

Central claim may not hold: The abstract claims reduced decoding latency, but the reported timing measures batched amortized cost per shot and does not establish single-shot or feedback latency. The reported speedups compare GPU neural decoding with CPU algorithmic baselines, so they apply to the stated implementations and hardware rather than a hardware-matched comparison. The accuracy benchmarks establish performance relative to selected algorithmic decoders, without independently establishing those decoders' proximity to optimal accuracy on the tested instances.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
5 pages, 4 figures with Methods. We will release the fully supplementary information in the second update soon

Related papers

Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation

Andi Gu, J. Pablo Bonilla Ataides, Mikhail D. Lukin +1 more

Quantum error correction (QEC) is essential for scalable quantum computing. However, it requires classical decoders that are fast and accurate enough to keep pace with quantum hardware. While quantum low-density parity-check codes have recently emerged as a promising route to efficient fault tolerance, current decoding algorithms do not allow one to realize the full potential of these codes in practical settings. Here, we introduce a convolutional neural network decoder that exploits the geometric structure of QEC codes, and use it to probe a novel "waterfall" regime of error suppression, demonstrating that the logical error rates required for large-scale fault-tolerant algorithms are attainable with modest code sizes at current physical error rates, and with latencies within the real-time budgets of several leading hardware platforms. For example, for the $[144, 12, 12]$ Gross code, the decoder achieves logical error rates up to $\sim 17$x below existing decoders - reaching logical error rates $\sim 10^{-10}$ at physical error $p=0.1\%$ - with 3-5 orders of magnitude higher throughput. This decoder also produces well-calibrated confidence estimates that can significantly reduce the time overhead of repeat-until-success protocols. Taken together, these results suggest that the space-time costs associated with fault-tolerant quantum computation may be significantly lower than previously anticipated.

quant-pharXiv:2604.08358•Apr 10, 2026•52 citations

HyperNQ: A Hypergraph Neural Network Decoder for Quantum LDPC Codes

Ameya S. Bhave, Navnil Choudhury, Kanad Basu

Quantum computing requires effective error correction strategies to mitigate noise and decoherence. Quantum Low-Density Parity-Check (QLDPC) codes have emerged as a promising solution for scalable Quantum Error Correction (QEC) applications by supporting constant-rate encoding and a sparse parity-check structure. However, decoding QLDPC codes via traditional approaches such as Belief Propagation (BP) suffers from poor convergence in the presence of short cycles. Machine learning techniques like Graph Neural Networks (GNNs) utilize learned message passing over their node features; however, they are restricted to pairwise interactions on Tanner graphs, which limits their ability to capture higher-order correlations. In this work, we propose HyperNQ, the first Hypergraph Neural Network (HGNN)- based QLDPC decoder that captures higher-order stabilizer constraints by utilizing hyperedges-thus enabling highly expressive and compact decoding. We use a two-stage message passing scheme and evaluate the decoder over the pseudo-threshold region. Below the pseudo-threshold mark, HyperNQ improves the Logical Error Rate (LER) up to 84% over BP and 50% over GNN-based strategies, demonstrating enhanced performance over the existing state-of-the-art decoders.

cs.LGCross-listedarXiv:2511.01741•International Conference on Communications•Nov 4, 2025•7 citations

Neural Decoders Reduce Logical Error Rates in Surface Code Quantum Systems

Lukas Schneider, Haruki Tanaka

Fault-tolerant quantum computation critically depends on the ability to detect and correct physical qubit errors faster than they accumulate. The surface code (SC) has emerged as the most experimentally promising quantum error correction (QEC) framework due to its high threshold and local stabilizer structure, yet its practical performance is bottlenecked by decoder efficiency. Traditional decoding approaches such as minimum-weight perfect matching (MWPM) achieve near-optimal accuracy under independent noise but struggle with correlated errors, circuit-level noise, and real-time latency constraints. This paper investigates how neural network (NN)-based decoders reduce logical error rates in SC quantum systems by learning complex syndrome-to-correction mappings from data. We propose a hybrid convolutional-recurrent neural architecture that processes stabilizer measurement syndromes across both spatial and temporal dimensions, enabling the decoder to capture correlated error patterns inherent in realistic hardware. Systematic simulations under depolarizing, biased, and circuit-level noise models demonstrate that the proposed neural decoder achieves a logical error rate reduction of up to 41.3% compared to MWPM at a physical error rate of p = 0.008, while maintaining sub-millisecond decoding latency compatible with superconducting qubit cycle times. These results establish that data-driven neural decoders represent a scalable and hardware-compatible pathway toward achieving the logical error rates required for practical fault-tolerant quantum computing.

Frontiers in Applied Physics and Mathematics•Mar 25, 2026•0 citations

Learning to Decode Trapping Sets in QLDPC Codes

Asit Kumar Pradhan, Nithin Raveendran, Narayanan Rengaswamy +2 more

Quantum low-density parity-check (QLDPC) codes with asymptotically nonzero rates are promising candidates for fault-tolerant quantum computation. Belief propagation (BP) based iterative decoding algorithms, a primary choice for classical LDPC codes, perform poorly for QLDPC codes due to stabilizer-induced trapping sets, resulting in a high error floor. Several decoding algorithms, like post-processing decoders, normalized BP decoders, and neural decoders, have been proposed to increase the performance in the error-floor region. However, this improvement comes at the expense of an increase in the execution time of the decoder. This paper proposes a general framework for error correction for a class of QLDPC codes called lifted-product codes using recurrent neural networks (RNNs). The RNN is employed to learn message-passing rules that can decode quantum-trapping sets. Then the standard message-passing rules are used with the learned rules to improve the error floor. While training the RNN, the quasi-cyclic property of the lifted product codes is exploited to reduce the size of the training set and the number of parameters in the network. This reduction in the number of parameters makes these decoders amenable to hardware implementation. Simulation results show that the proposed decoder performs better than the existing decoders in the literature.

International Symposium on Turbo Codes and Iterative Information Processing•Sep 4, 2023•5 citations

Adaptive decoding of quantum LDPC codes through decoder disagreement

Maida Wang, Peter V. Coveney

Accurate decoding of quantum low-density parity-check (qLDPC) codes often relies on expensive post-processing search, although decoding difficulty varies strongly between syndromes. We find that the benefit of deeper post-processing search is highly concentrated in a small subset of decoding instances, and that these instances can be identified directly from the decoder itself. To this end, we introduce an adaptive decoder based on belief propagation (BP) and ordered-statistics decoding (OSD), using the disagreement between the BP hard decision and the syndrome-consistent order-zero OSD solution as an internal risk signal to determine where deeper search is required. On a $[[144,12,12]]$ bivariate bicycle code under circuit-level depolarising noise, encoding $12$ logical qubits in $144$ data qubits with distance $12$, escalating only the highest-risk $20\%$ of instances recovers $85\%$ to $92\%$ of the improvement in logical error rate available from a full one-free-variable sweep, while reducing the mean serial decoding cost by a factor of $3.6$ relative to applying the same truncated search to every instance. At matched budget, disagreement-guided routing also outperforms routing based on the BP syndrome residual, syndrome weight and random selection. The same behaviour reappears on a structurally distinct radial qLDPC code obtained from a lifted-product construction, where escalating $20\%$ of instances recovers $87\%$ to $94\%$ of the available gain. A $Z$-memory experiment on the Quantinuum H2 trapped-ion processor, implementing both $X$-type and $Z$-type checks, further shows that the signal remains predictive under device noise. These results show that decoder-internal disagreement can expose where additional decoding effort is valuable, allowing classical computation to be concentrated on the instances most likely to benefit from it.

quant-pharXiv:2609.37629•Sep 30, 2026•0 citations

Accelerating BP-based decoders for QLDPC Codes with Local Syndrome-Based Preprocessing

Fan, Wenxuan, Yasunari Suzuki, Gokul Subramanian Ravi +4 more

Due to the high error rate of qubits, detecting and correcting errors is essential for achieving fault-tolerant quantum computing (FTQC). Quantum low-density parity-check (QLDPC) codes are one of the most promising quantum error correction (QEC) methods due to their high encoding rates. BP (Belief Propagation)-based decoders are widely used and highly competitive for QLDPC codes because BP offers inherent parallelism and strong scalability. However, BP-based decoders still suffer from high decoding latency, a large portion of which is spent in the iterative BP stage. In this paper, we propose a lightweight preprocessing step that utilizes local patterns in the syndrome to detect likely trivial error events and provide them as hints to BP-based decoders. These hints accelerate BP convergence and thereby reduce the overall decoding time. The proposed preprocessing step offers a broadly compatible approach to reducing the latency of BP-based QLDPC decodes. On the bivariate bicycle code $[[144,12,12]]$ at low physical error rates, our method achieves a $10\times$ speedup in decoding time for BP-OSD, and more than $2\times$ speedup for both BP-LSD and Relay-BP. Our method maintains the logical error rate when combined with BP-OSD and Relay-BP, while further achieving a significant reduction in logical error rate when combined with BP-LSD.

arXiv:2509.01892•Sep 2, 2025•2 citations
Quantum error correction is essential for fault-tolerant quantum computing. High-rate quantum low-density parity-check (qLDPC) codes have emerged as a promising approach to reducing the substantial physical qubit overhead of quantum error correction, enabling encoding rates exceeding 1/21/21/2 in blocks of approximately one thousand physical data qubits. However, their practical implementation requires decoders that combine high accuracy with low latency to keep pace with quantum hardware. Existing decoders of high-rate qLDPC codes can achieve high accuracy but often incur substantial computational latency, whereas neural network decoders have yet to be demonstrated for high-rate qLDPC codes. Here, we introduce \emph{neural triage decoding}, a framework that uses syndrome consistency to adaptively allocate neural computation. A local neural message-passing network rapidly predicts error corrections, additional iterations reduce residual syndrome violations, and a rarely invoked diversification stage searches for consistent corrections to the remaining shots. We demonstrate that the \texttt{Triage} decoder can decode ultra-high-rate qLDPC codes encoding a few hundred logical qubits, including lifted-product and Kasai codes, achieving state-of-the-art accuracy comparable to the near optimal algorithmic decoders while reducing decoding latency by approximately one to two orders of magnitude. Our framework is inspired by a rigorous analysis of the exact bitwise marginal decoder, revealing a distance-independent syndrome-inconsistent error floor. In addition, we show the robustness of neural network decoders to mismatched error priors. Our results establish adaptive neural decoding as a promising route towards fast, accurate, and scalable quantum error correction in the near term.
The paper addresses whether neural decoders can combine low logical error rates with manageable computational cost for high-rate qLDPC quantum memories. Its Triage framework applies a Tanner-graph neural message-passing decoder to the residual syndrome for up to four iterations, then escalates unresolved shots to searches using syndrome flips, prior perturbations and code symmetries. Syndrome-consistent candidates are ranked by likelihood under the original priors.
A theoretical analysis shows that exact bitwise MAP decisions can remain syndrome-inconsistent despite using exact marginals. Under specified graph assumptions and independent phenomenological noise, it proves Pinc=Ω(pκ(ν))P_{\mathrm{inc}}=\Omega(p^{\kappa(\nu)})Pinc​=Ω(pκ(ν)), where κ(ν)=ν/2+1\kappa(\nu)=\nu/2+1κ(ν)=ν/2+1 for even minimum qubit degree ν\nuν and ν+1\nu+1ν+1 for odd ν\nuν. Both benchmark matrices have ν=3\nu=3ν=3, yielding a quartic lower bound at fixed code size.
Monte Carlo benchmarks use the [[1122,148,d≤20]][[1122,148,d\leq20]][[1122,148,d≤20]] lifted-product code and [[1152,580,d≤12]][[1152,580,d\leq12]][[1152,580,d≤12]] Kasai code, with five and eight noisy measurement rounds respectively. At p=1.5%p=1.5\%p=1.5%, reported per-qubit-per-round logical error rates are 9.33×10−119.33\times10^{-11}9.33×10−11 and 5.08×10−105.08\times10^{-10}5.08×10−10. Full-decoder amortized costs are 2.372.372.37 and 12.312.312.3 ms per shot, versus 815815815 and 349349349 ms for the selected algorithmic baselines. Networks trained at p=2%p=2\%p=2% are evaluated across other error rates; separate frontend tests examine robustness to perturbed priors.
The timing comparison uses GPU batches of 64 versus CPU baselines, not matched-hardware single-shot latency. Benchmarks use phenomenological noise with perfect final extraction; circuit-level decoding, experimental validation, latency distributions, sustained real-time operation and online calibration remain untested.
Quantum error correction (QEC) is essential for scalable quantum computing. However, it requires classical decoders that are fast and accurate enough to keep pace with quantum hardware. While quantum low-density parity-check codes have recently emerged as a promising route to efficient fault tolerance, current decoding algorithms do not allow one to realize the full potential of these codes in practical settings. Here, we introduce a convolutional neural network decoder that exploits the geometric structure of QEC codes, and use it to probe a novel "waterfall" regime of error suppression, demonstrating that the logical error rates required for large-scale fault-tolerant algorithms are attainable with modest code sizes at current physical error rates, and with latencies within the real-time budgets of several leading hardware platforms. For example, for the [144,12,12][144, 12, 12][144,12,12] Gross code, the decoder achieves logical error rates up to ∼17\sim 17∼17x below existing decoders - reaching logical error rates ∼10−10\sim 10^{-10}∼10−10 at physical error p=0.1%p=0.1\%p=0.1% - with 3-5 orders of magnitude higher throughput. This decoder also produces well-calibrated confidence estimates that can significantly reduce the time overhead of repeat-until-success protocols. Taken together, these results suggest that the space-time costs associated with fault-tolerant quantum computation may be significantly lower than previously anticipated.
Quantum computing requires effective error correction strategies to mitigate noise and decoherence. Quantum Low-Density Parity-Check (QLDPC) codes have emerged as a promising solution for scalable Quantum Error Correction (QEC) applications by supporting constant-rate encoding and a sparse parity-check structure. However, decoding QLDPC codes via traditional approaches such as Belief Propagation (BP) suffers from poor convergence in the presence of short cycles. Machine learning techniques like Graph Neural Networks (GNNs) utilize learned message passing over their node features; however, they are restricted to pairwise interactions on Tanner graphs, which limits their ability to capture higher-order correlations. In this work, we propose HyperNQ, the first Hypergraph Neural Network (HGNN)- based QLDPC decoder that captures higher-order stabilizer constraints by utilizing hyperedges-thus enabling highly expressive and compact decoding. We use a two-stage message passing scheme and evaluate the decoder over the pseudo-threshold region. Below the pseudo-threshold mark, HyperNQ improves the Logical Error Rate (LER) up to 84% over BP and 50% over GNN-based strategies, demonstrating enhanced performance over the existing state-of-the-art decoders.
Fault-tolerant quantum computation critically depends on the ability to detect and correct physical qubit errors faster than they accumulate. The surface code (SC) has emerged as the most experimentally promising quantum error correction (QEC) framework due to its high threshold and local stabilizer structure, yet its practical performance is bottlenecked by decoder efficiency. Traditional decoding approaches such as minimum-weight perfect matching (MWPM) achieve near-optimal accuracy under independent noise but struggle with correlated errors, circuit-level noise, and real-time latency constraints. This paper investigates how neural network (NN)-based decoders reduce logical error rates in SC quantum systems by learning complex syndrome-to-correction mappings from data. We propose a hybrid convolutional-recurrent neural architecture that processes stabilizer measurement syndromes across both spatial and temporal dimensions, enabling the decoder to capture correlated error patterns inherent in realistic hardware. Systematic simulations under depolarizing, biased, and circuit-level noise models demonstrate that the proposed neural decoder achieves a logical error rate reduction of up to 41.3% compared to MWPM at a physical error rate of p = 0.008, while maintaining sub-millisecond decoding latency compatible with superconducting qubit cycle times. These results establish that data-driven neural decoders represent a scalable and hardware-compatible pathway toward achieving the logical error rates required for practical fault-tolerant quantum computing.
Quantum low-density parity-check (QLDPC) codes with asymptotically nonzero rates are promising candidates for fault-tolerant quantum computation. Belief propagation (BP) based iterative decoding algorithms, a primary choice for classical LDPC codes, perform poorly for QLDPC codes due to stabilizer-induced trapping sets, resulting in a high error floor. Several decoding algorithms, like post-processing decoders, normalized BP decoders, and neural decoders, have been proposed to increase the performance in the error-floor region. However, this improvement comes at the expense of an increase in the execution time of the decoder. This paper proposes a general framework for error correction for a class of QLDPC codes called lifted-product codes using recurrent neural networks (RNNs). The RNN is employed to learn message-passing rules that can decode quantum-trapping sets. Then the standard message-passing rules are used with the learned rules to improve the error floor. While training the RNN, the quasi-cyclic property of the lifted product codes is exploited to reduce the size of the training set and the number of parameters in the network. This reduction in the number of parameters makes these decoders amenable to hardware implementation. Simulation results show that the proposed decoder performs better than the existing decoders in the literature.
Accurate decoding of quantum low-density parity-check (qLDPC) codes often relies on expensive post-processing search, although decoding difficulty varies strongly between syndromes. We find that the benefit of deeper post-processing search is highly concentrated in a small subset of decoding instances, and that these instances can be identified directly from the decoder itself. To this end, we introduce an adaptive decoder based on belief propagation (BP) and ordered-statistics decoding (OSD), using the disagreement between the BP hard decision and the syndrome-consistent order-zero OSD solution as an internal risk signal to determine where deeper search is required. On a [[144,12,12]][[144,12,12]][[144,12,12]] bivariate bicycle code under circuit-level depolarising noise, encoding 121212 logical qubits in 144144144 data qubits with distance 121212, escalating only the highest-risk 20%20\%20% of instances recovers 85%85\%85% to 92%92\%92% of the improvement in logical error rate available from a full one-free-variable sweep, while reducing the mean serial decoding cost by a factor of 3.63.63.6 relative to applying the same truncated search to every instance. At matched budget, disagreement-guided routing also outperforms routing based on the BP syndrome residual, syndrome weight and random selection. The same behaviour reappears on a structurally distinct radial qLDPC code obtained from a lifted-product construction, where escalating 20%20\%20% of instances recovers 87%87\%87% to 94%94\%94% of the available gain. A ZZZ-memory experiment on the Quantinuum H2 trapped-ion processor, implementing both XXX-type and ZZZ-type checks, further shows that the signal remains predictive under device noise. These results show that decoder-internal disagreement can expose where additional decoding effort is valuable, allowing classical computation to be concentrated on the instances most likely to benefit from it.
Due to the high error rate of qubits, detecting and correcting errors is essential for achieving fault-tolerant quantum computing (FTQC). Quantum low-density parity-check (QLDPC) codes are one of the most promising quantum error correction (QEC) methods due to their high encoding rates. BP (Belief Propagation)-based decoders are widely used and highly competitive for QLDPC codes because BP offers inherent parallelism and strong scalability. However, BP-based decoders still suffer from high decoding latency, a large portion of which is spent in the iterative BP stage. In this paper, we propose a lightweight preprocessing step that utilizes local patterns in the syndrome to detect likely trivial error events and provide them as hints to BP-based decoders. These hints accelerate BP convergence and thereby reduce the overall decoding time. The proposed preprocessing step offers a broadly compatible approach to reducing the latency of BP-based QLDPC decodes. On the bivariate bicycle code [[144,12,12]][[144,12,12]][[144,12,12]] at low physical error rates, our method achieves a 10×10\times10× speedup in decoding time for BP-OSD, and more than 2×2\times2× speedup for both BP-LSD and Relay-BP. Our method maintains the logical error rate when combined with BP-OSD and Relay-BP, while further achieving a significant reduction in logical error rate when combined with BP-LSD.