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

IEEE Communications Letters

BP-LCGCD: A Gaussian-Elimination-Free and High-Performance Decoder for Surface Codes

Qianfan Wang, Jifan Liang, Lvzhou Li, Linqi Song, Xiao Ma

Published Dec 22, 2025• 1 citation
Publisher

Abstract

Belief propagation (BP) combined with ordered statistics decoding (OSD) can achieve near-optimal logical error rates for surface codes. However, OSD requires high-latency and unstable-complexity Gaussian elimination (GE), limiting its practicality. In this paper, we propose BP-LCGCD, a GE-free and high-performance decoder that replaces the GE-based OSD with the GE-free LC-GCD. Moreover, in contrast to the original BP-OSD, which adopts a single fixed normalization factor α, we further propose a list-parameterized variant, BP-LCGCD+ α, which performs multiple BP decodings with different α to generate diverse posterior LLRs. We present complexity analysis, demonstrating that at low physical error rates, the average decoding complexity of the proposed algorithm approaches that of standard BP. Simulation results demonstrate that BP-LCGCD achieves logical error rates close to BP-OSD, while BP-LCGCD+α nearly matches the performance of the BP-OSD. They also show that both proposed decoders significantly outperform standard BP and minimum-weight perfect matching (MWPM) in terms of logical error rate and threshold.

DOI
10.1109/lcomm.2025.3646724

Related papers

Gaussian-Elimination-Free BP-OSD Algorithm for Short 5G LDPC Codes

Qianfan Wang, Yiwen Wang, Jiayi Yang +2 more

In this paper, we propose a two-stage belief-propagation ordered statistics decoding (BP-OSD)-like algorithm, hereafter referred to as BP-LCGCD, tailored to 5G low-density parity-check (LDPC) codes. When standard BP decoding fails, a modified BP (mBP) with an iteration limit determined by the code’s girth and a normalization factor$\alpha $is performed to generate reliable posterior log-likelihood ratios (LLRs) in the pre-processing stage. In the post-processing stage, a locally constrained guessing codeword decoding (LC-GCD) module uses these posterior LLRs from the mBP to efficiently produce candidate codewords without any online Gaussian elimination (GE), where numerous invalid test error patterns are skipped by the introduced local constraints. To predict the decoding performance, we derive an upper bound on FER and employ a saddlepoint method to approximate its dominant tail-probability term, resulting in a semi-analytical FER prediction. Furthermore, we propose to design the second-stage LC-GCD to match the non-uniform posterior reliability profile induced by the BP-like preprocessing stage. To this end, an offline quasi-reliable re-encoding basis is constructed for 5G LDPC codes, where protograph EXIT-chart analysis is used to identify highly reliable variable-node positions. Simulation results demonstrate that the proposed GE-free BP-LCGCD significantly outperforms standard BP, achieves FER closely approaching that of GE-based BP-OSD, and approaches the finite-length bound across multiple code rates for 5G LDPC codes, while requiring a significantly smaller number of re-encodings and eliminating the need for online GE.

IEEE Transactions on Communications•Jan 1, 2026•0 citations

Logical Neural Belief Propagation for Linear-Complexity Decoding of Surface Codes

Hee-Youl Kwak, Seong-Joon Park, Dae-Young Yun +2 more

Quantum error correction (QEC) requires accurate and efficient decoders, yet belief propagation (BP), despite its linear decoding complexity, often provides insufficient logical accuracy on surface codes. We propose Logical Neural Belief Propagation (L-NBP), a BP-based neural decoder that redirects the decoding objective from physical-level to logical-level decoding. L-NBP uses a neural BP (NBP) module to produce posterior beliefs, which a logical classifier transforms into a continuous-valued soft syndrome for logical-operator prediction. Trained end-to-end by backpropagation, the NBP module learns soft syndromes that are favorable for logical classification. On surface codes, L-NBP matches or outperforms BP with ordered-statistics decoding (BP-OSD) and minimum-weight perfect matching (MWPM) while retaining the linear complexity of BP, and achieves a threshold of $17.5\%$ under depolarizing noise. Under circuit-level noise, L-NBP matches the accuracy of BP-OSD on the distance-$9$ surface code while requiring only $0.2\%$ of its complexity.

quant-pharXiv:2608.27682•Aug 31, 2026•1 citation

GE-Free BP-OSD for Short 5G LDPC Codes

Qianfan Wang, Yue Wang, Jiayi Yang +2 more

In this paper, we propose a two-stage beliefpropagation ordered statistics decoding (BP-OSD)-like algorithm, referred to as BP-LCGCD, tailored to 5G low-density paritycheck (LDPC) codes. When standard BP decoding fails, a modified BP (mBP) with an iteration limit determined by the code's girth and a normalization factor is performed to generate reliable posterior log-likelihood ratios (LLRs) in the pre-processing stage. In the post-processing stage, a locally constrained guessing codeword decoding (LC-GCD) module uses these posterior LLRs from mBP to produce candidate codewords without online Gaussian elimination (GE), where numerous invalid test error patterns (TEPs) are skipped by the introduced local constraints. To predict the performance, we derive an upper bound on FER and employ a saddlepoint method to compute its dominant tail-probability term. Furthermore, we propose an offline EXIT-chart-based method to select a fixed quasi-reliable basis, where variable nodes with the highest mutual information are chosen. Simulation results demonstrate that the proposed GE-free BP-LCGCD significantly outperforms standard BP, achieves FER very close to GE-based BP-OSD, and approaches the finite-length bound across multiple code rates for 5G LDPC codes, while requiring significantly fewer re-encodings and eliminating the need for online GE.

IEEE Wireless Communications and Networking Conference•Apr 13, 2026•1 citation

Achieving Thresholds via Standalone Belief Propagation on Surface Codes

Pedro Hack, Luca Menti, Francisco Lazaro +1 more

The standard approach to Belief Propagation (BP) decoding passes messages on the Tanner graph of the quantum error-correcting (QEC) code, and is known to lack a threshold for the surface code. We propose novel BP decoders that exchange messages on the decoding graph and obtain thresholds (both for code capacity and circuit-level noise) via standalone BP for the surface code under depolarizing noise. Our approach, similarly to the minimum weight perfect matching (MWPM) decoder, is applicable to any graphlike QEC code. The thresholds observed with our decoders are close to those obtained by MWPM. This result opens the path towards scalable hardware-accelerated implementations of MWPM-compatible decoders.

quant-pharXiv:2603.05381•Mar 6, 2026•2 citations

Low-Complexity BP-ORBOSD Algorithm for Short 5G LDPC Codes

Qianfan Wang, Yiwen Wang, Jiayi Yang +2 more

Belief propagation (BP) combined with ordered statistics decoding (OSD) achieves near-optimal frame error rate (FER) for short LDPC codes, but the extensive re-encoding overhead of OSD limits its practicality. To address this, we propose the BPORBOSD, a low-complexity and high-performance decoder that replaces conventional OSD with the ordered reliability bits OSD (ORBOSD), where the test error patterns are produced by the ORB technique. Moreover, in contrast to conventional BP-OSD, which directly adopts the soft information from standard BP into OSD after BP fails, we employ a modified BP scheme with a normalization factor α to produce soft reliability metrics better suited for ORBOSD. We derive the decoder’s complexity and demonstrate that, in the high-SNR regime, the average decoding complexity of BPORBOSD approaches that of standard BP. Simulation results confirm that BP-ORBOSD achieves FERs close to those of conventional BPOSD and the finite-length bound while significantly reducing the average number of re-encodings.

IEEE/CIC International Conference on Communications in China (ICCC)•Aug 10, 2025•1 citation

Evolutionary BP+OSD Decoding for Low-Latency Quantum Error Correction

Hee-Youl Kwak, Seong-Joon Park, Hyunwoo Jung +2 more

Quantum error correction (QEC) for fault-tolerant quantum computing requires a balanced decoding solution that offers high performance, low complexity, and low latency. However, the de facto standard - belief propagation (BP) combined with ordered statistics decoding (OSD) - suffers from excessive iterations in the BP stage and high complexity in the OSD stage. To address these challenges, we propose an evolutionary BP (EBP) decoder optimized via a differential evolution (DE) algorithm. By leveraging the gradient-free nature of DE, we enable end-to-end optimization of the EBP+OSD structure to maximize overall performance. In addition, a multi-objective selection rule is introduced to suppress frequent OSD activation, significantly reducing complexity overhead. Simulation results on surface codes and quantum low-density parity-check (QLDPC) codes demonstrate that EBP+OSD simultaneously achieves both superior decoding performance and substantially lower complexity compared to conventional BP+OSD, particularly in stringent low-latency regimes.

quant-pharXiv:2512.18273•IEEE Journal on Selected Areas in Communications•Dec 23, 2025•2 citations
Belief propagation (BP) combined with ordered statistics decoding (OSD) can achieve near-optimal logical error rates for surface codes. However, OSD requires high-latency and unstable-complexity Gaussian elimination (GE), limiting its practicality. In this paper, we propose BP-LCGCD, a GE-free and high-performance decoder that replaces the GE-based OSD with the GE-free LC-GCD. Moreover, in contrast to the original BP-OSD, which adopts a single fixed normalization factor α, we further propose a list-parameterized variant, BP-LCGCD+ α, which performs multiple BP decodings with different α to generate diverse posterior LLRs. We present complexity analysis, demonstrating that at low physical error rates, the average decoding complexity of the proposed algorithm approaches that of standard BP. Simulation results demonstrate that BP-LCGCD achieves logical error rates close to BP-OSD, while BP-LCGCD+α nearly matches the performance of the BP-OSD. They also show that both proposed decoders significantly outperform standard BP and minimum-weight perfect matching (MWPM) in terms of logical error rate and threshold.
In this paper, we propose a two-stage belief-propagation ordered statistics decoding (BP-OSD)-like algorithm, hereafter referred to as BP-LCGCD, tailored to 5G low-density parity-check (LDPC) codes. When standard BP decoding fails, a modified BP (mBP) with an iteration limit determined by the code’s girth and a normalization factor$\alpha $is performed to generate reliable posterior log-likelihood ratios (LLRs) in the pre-processing stage. In the post-processing stage, a locally constrained guessing codeword decoding (LC-GCD) module uses these posterior LLRs from the mBP to efficiently produce candidate codewords without any online Gaussian elimination (GE), where numerous invalid test error patterns are skipped by the introduced local constraints. To predict the decoding performance, we derive an upper bound on FER and employ a saddlepoint method to approximate its dominant tail-probability term, resulting in a semi-analytical FER prediction. Furthermore, we propose to design the second-stage LC-GCD to match the non-uniform posterior reliability profile induced by the BP-like preprocessing stage. To this end, an offline quasi-reliable re-encoding basis is constructed for 5G LDPC codes, where protograph EXIT-chart analysis is used to identify highly reliable variable-node positions. Simulation results demonstrate that the proposed GE-free BP-LCGCD significantly outperforms standard BP, achieves FER closely approaching that of GE-based BP-OSD, and approaches the finite-length bound across multiple code rates for 5G LDPC codes, while requiring a significantly smaller number of re-encodings and eliminating the need for online GE.
Quantum error correction (QEC) requires accurate and efficient decoders, yet belief propagation (BP), despite its linear decoding complexity, often provides insufficient logical accuracy on surface codes. We propose Logical Neural Belief Propagation (L-NBP), a BP-based neural decoder that redirects the decoding objective from physical-level to logical-level decoding. L-NBP uses a neural BP (NBP) module to produce posterior beliefs, which a logical classifier transforms into a continuous-valued soft syndrome for logical-operator prediction. Trained end-to-end by backpropagation, the NBP module learns soft syndromes that are favorable for logical classification. On surface codes, L-NBP matches or outperforms BP with ordered-statistics decoding (BP-OSD) and minimum-weight perfect matching (MWPM) while retaining the linear complexity of BP, and achieves a threshold of 17.5%17.5\%17.5% under depolarizing noise. Under circuit-level noise, L-NBP matches the accuracy of BP-OSD on the distance-999 surface code while requiring only 0.2%0.2\%0.2% of its complexity.
In this paper, we propose a two-stage beliefpropagation ordered statistics decoding (BP-OSD)-like algorithm, referred to as BP-LCGCD, tailored to 5G low-density paritycheck (LDPC) codes. When standard BP decoding fails, a modified BP (mBP) with an iteration limit determined by the code's girth and a normalization factor is performed to generate reliable posterior log-likelihood ratios (LLRs) in the pre-processing stage. In the post-processing stage, a locally constrained guessing codeword decoding (LC-GCD) module uses these posterior LLRs from mBP to produce candidate codewords without online Gaussian elimination (GE), where numerous invalid test error patterns (TEPs) are skipped by the introduced local constraints. To predict the performance, we derive an upper bound on FER and employ a saddlepoint method to compute its dominant tail-probability term. Furthermore, we propose an offline EXIT-chart-based method to select a fixed quasi-reliable basis, where variable nodes with the highest mutual information are chosen. Simulation results demonstrate that the proposed GE-free BP-LCGCD significantly outperforms standard BP, achieves FER very close to GE-based BP-OSD, and approaches the finite-length bound across multiple code rates for 5G LDPC codes, while requiring significantly fewer re-encodings and eliminating the need for online GE.
The standard approach to Belief Propagation (BP) decoding passes messages on the Tanner graph of the quantum error-correcting (QEC) code, and is known to lack a threshold for the surface code. We propose novel BP decoders that exchange messages on the decoding graph and obtain thresholds (both for code capacity and circuit-level noise) via standalone BP for the surface code under depolarizing noise. Our approach, similarly to the minimum weight perfect matching (MWPM) decoder, is applicable to any graphlike QEC code. The thresholds observed with our decoders are close to those obtained by MWPM. This result opens the path towards scalable hardware-accelerated implementations of MWPM-compatible decoders.
Belief propagation (BP) combined with ordered statistics decoding (OSD) achieves near-optimal frame error rate (FER) for short LDPC codes, but the extensive re-encoding overhead of OSD limits its practicality. To address this, we propose the BPORBOSD, a low-complexity and high-performance decoder that replaces conventional OSD with the ordered reliability bits OSD (ORBOSD), where the test error patterns are produced by the ORB technique. Moreover, in contrast to conventional BP-OSD, which directly adopts the soft information from standard BP into OSD after BP fails, we employ a modified BP scheme with a normalization factor α to produce soft reliability metrics better suited for ORBOSD. We derive the decoder’s complexity and demonstrate that, in the high-SNR regime, the average decoding complexity of BPORBOSD approaches that of standard BP. Simulation results confirm that BP-ORBOSD achieves FERs close to those of conventional BPOSD and the finite-length bound while significantly reducing the average number of re-encodings.
Quantum error correction (QEC) for fault-tolerant quantum computing requires a balanced decoding solution that offers high performance, low complexity, and low latency. However, the de facto standard - belief propagation (BP) combined with ordered statistics decoding (OSD) - suffers from excessive iterations in the BP stage and high complexity in the OSD stage. To address these challenges, we propose an evolutionary BP (EBP) decoder optimized via a differential evolution (DE) algorithm. By leveraging the gradient-free nature of DE, we enable end-to-end optimization of the EBP+OSD structure to maximize overall performance. In addition, a multi-objective selection rule is introduced to suppress frequent OSD activation, significantly reducing complexity overhead. Simulation results on surface codes and quantum low-density parity-check (QLDPC) codes demonstrate that EBP+OSD simultaneously achieves both superior decoding performance and substantially lower complexity compared to conventional BP+OSD, particularly in stringent low-latency regimes.