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:2307.06575

Deep learning based enhancement of ordered statistics decoding of short LDPC codes

Guangwen Li, Yu Xiao

Published Jul 13, 2023• 0 citations
arXivHTMLPDF

Abstract

In the search for highly efficient decoders for short LDPC codes approaching maximum likelihood performance, a relayed decoding strategy, specifically activating the ordered statistics decoding process upon failure of a neural min-sum decoder, is enhanced by instilling three innovations. Firstly, soft information gathered at each step of the neural min-sum decoder is leveraged to forge a new reliability measure using a convolutional neural network. This measure aids in constructing the most reliable basis of ordered statistics decoding, bolstering the decoding process by excluding error-prone bits or concentrating them in a smaller area. Secondly, an adaptive ordered statistics decoding process is introduced, guided by a derived decoding path comprising prioritized blocks, each containing distinct test error patterns. The priority of these blocks is determined from the statistical data during the query phase. Furthermore, effective complexity management methods are devised by adjusting the decoding path's length or refining constraints on the involved blocks. Thirdly, a simple auxiliary criterion is introduced to reduce computational complexity by minimizing the number of candidate codewords before selecting the optimal estimate. Extensive experimental results and complexity analysis strongly support the proposed framework, demonstrating its advantages in terms of high throughput, low complexity, independence from noise variance, in addition to superior decoding performance.

DOI
10.48550/arxiv.2307.06575

Related papers

The impact when neural min-sum variant meets ordered statistics decoding of LDPC codes

Guangwen Li, Xiao Yu

This paper introduces three key initiatives in the pursuit of a hybrid decoding framework characterized by superior decoding performance, high throughput, low complexity, and independence from channel noise variance. Firstly, adopting a graphical neural network perspective, we propose a design methodology for a family of neural min-sum variants. Our exploration delves into the frame error rates associated with different decoding variants and the consequential impact of decoding failures on subsequent ordered statistics decoding. Notably, these neural min-sum variants exhibit generally indistinguishable performance, hence the simplest member is chosen as the constituent of the hybrid decoding. Secondly, to address computational complexities arising from exhaustive searches for authentic error patterns in cases of decoding failure, two alternatives for ordered statistics decoding implementation are proposed. The first approach involves uniformly grouping test error patterns, while the second scheme dynamically generates qualified searching test error patterns with varied sizes for each group. In both methods, group priorities are determined empirically. Thirdly, iteration diversity is highlighted in the case of LDPC codes requiring high maximum iterations of decoding. This is achieved by segmenting the long iterative decoding trajectory of a decoding failure into shorter segments, which are then independently fed to small models to enhance the chances of acquiring the authentic error pattern. These ideas are substantiated through extensive simulation results covering the codes with block lengths ranging from one hundred to several hundreds.

arXiv:2310.07129•Oct 11, 2023•0 citations

Boosting Ordered Statistics Decoding of Short LDPC Codes With Simple Neural Network Models

Guangwen Li, Xiao Yu

Ordered statistics decoding has been instrumental in addressing decoding failures that persist after normalized min-sum decoding in short low-density parity-check codes. Despite its benefits, the high computational complexity of effective ordered statistics decoding has limited its application in complexity-sensitive scenarios. To mitigate this issue, we propose a novel variant of the ordered statistics decoder. This approach begins with the design of a neural network model that refines the measurement of codeword bits, utilizing iterative information from normalized min-sum decoding failures. Subsequently, a fixed decoding path is established, comprising a sequence of blocks, each featuring a variety of test error patterns. The introduction of a sliding window-assisted neural model facilitates early termination of the ordered statistics decoding process along this path, aiming to balance performance and computational complexity. Comprehensive simulations and complexity analyses demonstrate that the proposed hybrid method matches state-of-the-art approaches across various metrics, particularly excelling in reducing latency.

arXiv:2404.14165•IEEE Communications Letters•Oct 7, 2024•5 citations

Neural-model-augmented hybrid NMS-OSD decoders for near-ML in short block codes

Guangwen Li, Yu Xiao

Abstract This paper introduces a hybrid decoding architecture that serially couples a normalized min-sum (NMS) decoder with reinforced ordered statistics decoding (OSD) to achieve near-maximum likelihood (ML) performance for short linear block codes. The framework incorporates several key innovations: a decoding information aggregation model that employs a convolutional neural network to refine bit reliability estimates for OSD using the soft-output trajectory of the NMS decoder; an adaptive decoding path for OSD, initialized by the arranged list of the most a priori likely tests algorithm and dynamically updated with empirical data; and a sliding window assisted model that enables early termination of test error patterns’ traversal, curbing complexity with minimal performance loss. For short high-rate codes, a dedicated undetected error detector identifies erroneous NMS outcomes that satisfy parity checks, ensuring they are forwarded to OSD for correction. Extensive simulations on LDPC, BCH, and RS codes demonstrate that the proposed hybrid decoder delivers a competitive trade-off, achieving near-ML frame error rate performance while maintaining advantages in throughput, latency, and complexity over state-of-the-art alternatives.

arXiv:2509.25580•Journal on Wireless Communications and Networking•Jun 27, 2026•0 citations

Generalized reliability-based syndrome decoding for LDPC codes

Guangwen Li, Guangzeng Feng

Aiming at bridging the gap between the maximum likelihood decoding (MLD) and the suboptimal iterative decodings for short or medium length LDPC codes, we present a generalized ordered statistic decoding (OSD) in the form of syndrome decoding, to cascade with the belief propagation (BP) or enhanced min-sum decoding. The OSD is invoked only when the decoding failures are obtained for the preceded iterative decoding method. With respect to the existing OSD which is based on the accumulated log-likelihood ratio (LLR) metric, we extend the accumulative metric to the situation where the BP decoding is in the probability domain. Moreover, after generalizing the accumulative metric to the context of the normalized or offset min-sum decoding, the OSD shows appealing tradeoff between performance and complexity. In the OSD implementation, when deciding the true error pattern among many candidates, an alternative proposed proves to be effective to reduce the number of real additions without performance loss. Simulation results demonstrate that the cascade connection of enhanced min-sum and OSD decodings outperforms the BP alone significantly, in terms of either performance or complexity.

arXiv:0710.5230•Oct 27, 2007•0 citations

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

Hee-Youl Kwak, Dae-Young Yun, Yongjune Kim +2 more

Low-density parity-check (LDPC) codes have been successfully commercialized in communication systems due to their strong error correction capabilities and simple decoding process. However, the error-floor phenomenon of LDPC codes, in which the error rate stops decreasing rapidly at a certain level, presents challenges for achieving extremely low error rates and deploying LDPC codes in scenarios demanding ultra-high reliability. In this work, we propose training methods for neural min-sum (NMS) decoders to eliminate the error-floor effect. First, by leveraging the boosting learning technique of ensemble networks, we divide the decoding network into two neural decoders and train the post decoder to be specialized for uncorrected words that the first decoder fails to correct. Secondly, to address the vanishing gradient issue in training, we introduce a block-wise training schedule that locally trains a block of weights while retraining the preceding block. Lastly, we show that assigning different weights to unsatisfied check nodes effectively lowers the error-floor with a minimal number of weights. By applying these training methods to standard LDPC codes, we achieve the best error-floor performance compared to other decoding methods. The proposed NMS decoder, optimized solely through novel training methods without additional modules, can be integrated into existing LDPC decoders without incurring extra hardware costs. The source code is available at https://github.com/ghy1228/LDPC_Error_Floor .

arXiv:2310.07194•neural information processing systems•Jan 1, 2023•11 citations

A Layer-Wise Syndrome-Based Framework for LDPC Decoding with Deep Learning

Ziwen Ren

This paper proposes a newly developed layer-wise syndrome-based framework for decoding Low-Density Parity-Check (LDPC) codes using deep learning. The framework leverages a layer-specific training approach to design methodologically effective decoding strategies, aiming to utilize the specific characteristics of each layer and improve overall decoding performance. By integrating the Normalized Offset Min-Sum (NOMS) algorithm into a Forward-Feedback Neural Network (NOMS-FF), the proposed model employs a soft-syndrome loss function to assist the learning of codeword structures and optimize decoding performance across varying noise levels. Additionally, the framework incorporates a layer-freezing strategy and dynamic Signal-to-Noise Ratio (SNR) allocation, enabling targeted post-training adjustments tailored to layer-specific characteristics. Experimental results on 6G-candidate QC-LDPC codes (Base Graph 2, N=240,K=80 ) demonstrate that the proposed approach provides substantial performance advantages over traditional decoders across the entire SNR range tested in this study. Furthermore, this study conducts partial-layer decoding experiments, which demonstrate that using only a subset of neural network layers can reduce the model’s computational runtime while simultaneously maintaining or improving decoding accuracy compared to the full-layer model under specific noise conditions.

•Jan 1, 2026•0 citations
In the search for highly efficient decoders for short LDPC codes approaching maximum likelihood performance, a relayed decoding strategy, specifically activating the ordered statistics decoding process upon failure of a neural min-sum decoder, is enhanced by instilling three innovations. Firstly, soft information gathered at each step of the neural min-sum decoder is leveraged to forge a new reliability measure using a convolutional neural network. This measure aids in constructing the most reliable basis of ordered statistics decoding, bolstering the decoding process by excluding error-prone bits or concentrating them in a smaller area. Secondly, an adaptive ordered statistics decoding process is introduced, guided by a derived decoding path comprising prioritized blocks, each containing distinct test error patterns. The priority of these blocks is determined from the statistical data during the query phase. Furthermore, effective complexity management methods are devised by adjusting the decoding path's length or refining constraints on the involved blocks. Thirdly, a simple auxiliary criterion is introduced to reduce computational complexity by minimizing the number of candidate codewords before selecting the optimal estimate. Extensive experimental results and complexity analysis strongly support the proposed framework, demonstrating its advantages in terms of high throughput, low complexity, independence from noise variance, in addition to superior decoding performance.
This paper introduces three key initiatives in the pursuit of a hybrid decoding framework characterized by superior decoding performance, high throughput, low complexity, and independence from channel noise variance. Firstly, adopting a graphical neural network perspective, we propose a design methodology for a family of neural min-sum variants. Our exploration delves into the frame error rates associated with different decoding variants and the consequential impact of decoding failures on subsequent ordered statistics decoding. Notably, these neural min-sum variants exhibit generally indistinguishable performance, hence the simplest member is chosen as the constituent of the hybrid decoding. Secondly, to address computational complexities arising from exhaustive searches for authentic error patterns in cases of decoding failure, two alternatives for ordered statistics decoding implementation are proposed. The first approach involves uniformly grouping test error patterns, while the second scheme dynamically generates qualified searching test error patterns with varied sizes for each group. In both methods, group priorities are determined empirically. Thirdly, iteration diversity is highlighted in the case of LDPC codes requiring high maximum iterations of decoding. This is achieved by segmenting the long iterative decoding trajectory of a decoding failure into shorter segments, which are then independently fed to small models to enhance the chances of acquiring the authentic error pattern. These ideas are substantiated through extensive simulation results covering the codes with block lengths ranging from one hundred to several hundreds.
Ordered statistics decoding has been instrumental in addressing decoding failures that persist after normalized min-sum decoding in short low-density parity-check codes. Despite its benefits, the high computational complexity of effective ordered statistics decoding has limited its application in complexity-sensitive scenarios. To mitigate this issue, we propose a novel variant of the ordered statistics decoder. This approach begins with the design of a neural network model that refines the measurement of codeword bits, utilizing iterative information from normalized min-sum decoding failures. Subsequently, a fixed decoding path is established, comprising a sequence of blocks, each featuring a variety of test error patterns. The introduction of a sliding window-assisted neural model facilitates early termination of the ordered statistics decoding process along this path, aiming to balance performance and computational complexity. Comprehensive simulations and complexity analyses demonstrate that the proposed hybrid method matches state-of-the-art approaches across various metrics, particularly excelling in reducing latency.
Abstract This paper introduces a hybrid decoding architecture that serially couples a normalized min-sum (NMS) decoder with reinforced ordered statistics decoding (OSD) to achieve near-maximum likelihood (ML) performance for short linear block codes. The framework incorporates several key innovations: a decoding information aggregation model that employs a convolutional neural network to refine bit reliability estimates for OSD using the soft-output trajectory of the NMS decoder; an adaptive decoding path for OSD, initialized by the arranged list of the most a priori likely tests algorithm and dynamically updated with empirical data; and a sliding window assisted model that enables early termination of test error patterns’ traversal, curbing complexity with minimal performance loss. For short high-rate codes, a dedicated undetected error detector identifies erroneous NMS outcomes that satisfy parity checks, ensuring they are forwarded to OSD for correction. Extensive simulations on LDPC, BCH, and RS codes demonstrate that the proposed hybrid decoder delivers a competitive trade-off, achieving near-ML frame error rate performance while maintaining advantages in throughput, latency, and complexity over state-of-the-art alternatives.
Aiming at bridging the gap between the maximum likelihood decoding (MLD) and the suboptimal iterative decodings for short or medium length LDPC codes, we present a generalized ordered statistic decoding (OSD) in the form of syndrome decoding, to cascade with the belief propagation (BP) or enhanced min-sum decoding. The OSD is invoked only when the decoding failures are obtained for the preceded iterative decoding method. With respect to the existing OSD which is based on the accumulated log-likelihood ratio (LLR) metric, we extend the accumulative metric to the situation where the BP decoding is in the probability domain. Moreover, after generalizing the accumulative metric to the context of the normalized or offset min-sum decoding, the OSD shows appealing tradeoff between performance and complexity. In the OSD implementation, when deciding the true error pattern among many candidates, an alternative proposed proves to be effective to reduce the number of real additions without performance loss. Simulation results demonstrate that the cascade connection of enhanced min-sum and OSD decodings outperforms the BP alone significantly, in terms of either performance or complexity.
Low-density parity-check (LDPC) codes have been successfully commercialized in communication systems due to their strong error correction capabilities and simple decoding process. However, the error-floor phenomenon of LDPC codes, in which the error rate stops decreasing rapidly at a certain level, presents challenges for achieving extremely low error rates and deploying LDPC codes in scenarios demanding ultra-high reliability. In this work, we propose training methods for neural min-sum (NMS) decoders to eliminate the error-floor effect. First, by leveraging the boosting learning technique of ensemble networks, we divide the decoding network into two neural decoders and train the post decoder to be specialized for uncorrected words that the first decoder fails to correct. Secondly, to address the vanishing gradient issue in training, we introduce a block-wise training schedule that locally trains a block of weights while retraining the preceding block. Lastly, we show that assigning different weights to unsatisfied check nodes effectively lowers the error-floor with a minimal number of weights. By applying these training methods to standard LDPC codes, we achieve the best error-floor performance compared to other decoding methods. The proposed NMS decoder, optimized solely through novel training methods without additional modules, can be integrated into existing LDPC decoders without incurring extra hardware costs. The source code is available at https://github.com/ghy1228/LDPC_Error_Floor .
This paper proposes a newly developed layer-wise syndrome-based framework for decoding Low-Density Parity-Check (LDPC) codes using deep learning. The framework leverages a layer-specific training approach to design methodologically effective decoding strategies, aiming to utilize the specific characteristics of each layer and improve overall decoding performance. By integrating the Normalized Offset Min-Sum (NOMS) algorithm into a Forward-Feedback Neural Network (NOMS-FF), the proposed model employs a soft-syndrome loss function to assist the learning of codeword structures and optimize decoding performance across varying noise levels. Additionally, the framework incorporates a layer-freezing strategy and dynamic Signal-to-Noise Ratio (SNR) allocation, enabling targeted post-training adjustments tailored to layer-specific characteristics. Experimental results on 6G-candidate QC-LDPC codes (Base Graph 2, N=240,K=80 ) demonstrate that the proposed approach provides substantial performance advantages over traditional decoders across the entire SNR range tested in this study. Furthermore, this study conducts partial-layer decoding experiments, which demonstrate that using only a subset of neural network layers can reduce the model’s computational runtime while simultaneously maintaining or improving decoding accuracy compared to the full-layer model under specific noise conditions.