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

Entropy

RL-Based Parallel LDPC Decoding with Clustered Scheduling

Yusuf Ozkan, Yauhen Yakimenka, Jörg Kliewer

Published Feb 12, 2026• 1 citation
Publisher

Abstract

We propose a reinforcement learning (RL)-based decoding framework for high-throughput parallel decoding of low-density parity-check (LDPC) codes using clustered scheduling. Parallel LDPC decoders must balance error-correction performance and decoding latency while avoiding memory conflicts. To address this trade-off, we construct clusters of check nodes that satisfy a two-edge independence property, which enables conflict-free row-parallel belief propagation. An RL agent is trained offline to assign Q-values to clusters and to prioritize their update order during decoding. To overcome the exponential storage requirements of existing RL-based scheduling methods, we introduce the Q-Sum method, which approximates cluster-level Q-values as the sum of Q-values of individual check nodes, reducing storage complexity from exponential to linear in the number of check nodes. We further propose an On-the-Fly clustering strategy that enforces two-edge independence dynamically during decoding and provides additional flexibility when static clustering is not feasible. Simulation results for array-based LDPC codes over additive white Gaussian noise (AWGN) channels show that the proposed methods improve the latency-versus-performance trade-off of parallel LDPC decoders, achieving lower decoding latency and higher throughput while maintaining error rates comparable to state-of-the-art decoding methods.

DOI
10.3390/e28020215

Related papers

Conflict-Free Color-Clustered Sequential Belief-Propagation Decoding of Quantum LDPC Codes via Reinforcement Learning

Mohsen Moradi, Taejoon Kim, Rémi A. Chou

Belief-propagation (BP) decoding for quantum low-density parity-check (QLDPC) codes is attractive due to its low complexity and low latency, but it is often limited by short cycles, degeneracy, and convergence failures. Reinforcement-learning-based sequential BP decoding (RL-S) improves BP by learning a syndrome-dependent variable-node (VN) update order, but its VN-by-VN schedule has limited within-iteration parallelism. In this paper, we propose a conflict-free color-clustered extension of RL-S. We construct a VN conflict graph in which two VNs are adjacent if they share an X-type or Z-type check, and color this graph so that same-color VNs have disjoint check neighborhoods. This also prevents VNs from the same Tanner 4- or 6-cycle from being updated simultaneously. During decoding, the trained VN-level Q-table selects a seed VN, and all remaining VNs with the same color are updated in parallel using the same pre-batch messages. For the [[288,12,18]] bivariate-bicycle code over the depolarizing channel, our proposed decoder achieves block-error-rate performance close to VN-level RL-S while reducing the scheduling decisions from 288 VNs to 11 color classes per BP iteration.

arXiv:2609.20236•Sep 2, 2026•1 citation

Learning to Decode Quantum LDPC Codes via Cluster-Based Sequential Belief Propagation

Mohsen Moradi, Taejoon Kim, Rémi A. Chou +1 more

Belief-propagation (BP) decoding for quantum low-density parity-check (QLDPC) codes is attractive due to its low complexity, but its performance is often limited by short cycles, degeneracy, and convergence failures. Recently, reinforcement-learning-based sequential variable-node (VN) scheduling (RL-S) was shown to improve BP decoding by learning state-dependent update orders. However, the VN-by-VN nature of that approach offers limited within-iteration parallelism, since only one VN is updated at a time. In this paper, we propose a cluster-based extension of RL-S for QLDPC codes. The VNs are partitioned into fixed clusters, and at each scheduling step the RL agent selects one cluster to update, after which all VNs in that cluster are updated in parallel using the same pre-update incoming messages. To keep the tabular state space practical for large cluster sizes, we introduce a permutation-invariant cluster state based on a normalized histogram of local mismatch weights, followed by quantization. This representation makes the number of cluster states depend on the quantization resolution rather than the cluster size. We also develop the corresponding cluster-level Markov decision process, reward function, and Q-learning update. Numerical results on representative QLDPC codes show that the proposed clustered learned scheduling preserves most of the error-rate benefit of VN-level learned sequential scheduling while substantially reducing the number of scheduling decisions per BP iteration, thereby providing an attractive latency-parallelism tradeoff.

cs.ITCross-listedarXiv:2607.20130•Jul 23, 2026•4 citations

Belief Propagation Decoding of Short Graph-Based Channel Codes via Reinforcement Learning

Salman Habib, Allison Beemer, Jörg Kliewer

In this work, we consider the decoding of short sparse graph-based channel codes via reinforcement learning (RL). Specifically, we focus on low-density parity-check (LDPC) codes, which for example have been standardized in the context of 5G cellular communication systems due to their excellent error correcting performance. LDPC codes are typically decoded via belief propagation on the corresponding bipartite (Tanner) graph of the code via flooding, i.e., all check and variable nodes in the Tanner graph are updated at once. We model the node-wise sequential LDPC scheduling scheme as a Markov decision process (MDP), and obtain optimized check node (CN) scheduling policies via RL to improve sequential decoding performance as compared to flooding. In each RL step, an agent decides which CN to schedule next by observing a reward associated with each choice. Repeated scheduling enables the agent to discover the optimized CN scheduling policy which is later incorporated in our RL-based sequential LDPC decoder. In order to reduce RL complexity, we propose a novel graph-induced CN clustering approach to partition the state space of the MDP in such a way that dependencies between clusters are minimized. Compared to standard decoding approaches from the literature, some of our proposed RL schemes not only improve the decoding performance, but also reduce the decoding complexity dramatically once the scheduling policy is learned. By concatenating an outer Hamming code with an inner LDPC code which is decoded based on our learned policy, we demonstrate significant improvements in the decoding performance compared to other LDPC decoding policies.

arXiv:2010.05637•IEEE Journal on Selected Areas in Information Theory•Apr 16, 2021•29 citations

Low-Latency Belief-Propagation Decoding of Quantum LDPC Codes with Reinforcement-Learned Scheduling

Mohsen Moradi, Ghilas Aissou, Taejoon Kim +2 more

Belief propagation (BP) is attractive for quantum low-density parity-check (QLDPC) decoding because of its low complexity and low latency, but short cycles and degeneracy can limit its error-correction performance. Reinforcement-learned sequential scheduling (RL-S) substantially improves this performance by adapting the variable node (VN) update order, although Q-table storage and heap-based selection introduce additional overhead. We propose bucket RL-S (B-RL-S), which quantizes learned Q-values into integer priorities and schedules VN updates using dynamically maintained first-in, first-out buckets. Without retraining or changing the BP message updates, B-RL-S reduces policy storage and refreshes only priorities affected by local residual syndrome changes. A fixed number of priority levels enables constant-time VN selection and queue relocation. For the $[[288,12,18]]$ bivariate bicycle code over the depolarizing channel at $p=0.05$, B-RL-S with eight priority levels achieves approximately one fifth the block error rate (BLER) of flooding BP followed by order-10 ordered-statistics decoding. The respective caps are $1000$ sequential iterations for B-RL-S and $1000$ flooding iterations for the BP stage of the reference decoder. These results highlight strong error correction with inexpensive scheduling and no additional post-processing stage.

arXiv:2610.15857•Oct 11, 2026•1 citation

Learning to Decode Quantum LDPC Codes Via Belief Propagation

Mohsen Moradi, Vahid Nourozi, Salman Habib +1 more

Belief-propagation (BP) decoding for quantum low-density parity-check (QLDPC) codes is appealing due to its low complexity, yet it often exhibits convergence issues due to quantum degeneracy and short cycles that exist in the Tanner graph. To overcome this challenge, this paper proposes a reinforcement-learning (RL) approach that learns (offline) how to decode QLDPC codes based on sequential decoding trajectories. The decoding is formulated as a Markov decision process with a local, syndrome-driven state representation of the underlying RL agent. To enable fast inference, critical for practical implementation, we incrementally update our RL-based QLDPC decoder using second-order neighborhoods that avoid global rescans. Simulation results on representative QLDPC codes demonstrate the superiority of the proposed RL-based QLDPC decoders in terms of performance and convergence speed when compared to flooding and random sequential schedules, while achieving performance competitive with state-of-the-art BP-based decoders at comparable complexity.

arXiv:2603.10192•Mar 10, 2026•9 citations

Low-Complexity LDPC Decoding Algorithm Based on Layered Vicinal Variable Node Scheduling

Mhammed Benhayoun, Mouhcine Razi, Anas Mansouri +1 more

The informed dynamic scheduling (IDS) strategies for the low-density parity check (LDPC) decoding have shown superior performance in error correction and convergence speed, particularly those based on reliability measures and residual belief propagation (RBP). However, the search for the most unreliable variable nodes and the residual precomputation required for each iteration of the IDS-LDPC increases the complexity of the decoding process which becomes more sequential, making it hard to exploit the parallelism of signal processing algorithms available in multicore platforms. To overcome this problem, a new, low-complexity scheduling system, called layered vicinal variable nodes scheduling (LWNS) is presented in this paper. With this LWNS, each variable node is updated by exchanging intrinsic information with all its associated control and variable nodes before moving to the next variable node updating. The proposed scheduling strategy is fixed by a preprocessing step of the parity control matrix instead of calculation of the residuals values and by computation of the most influential variable node instead the most unreliable metric. It also allows the parallel processing of independent Tanner graph subbranches identified and grouped in layers. Our simulation results show that the LWNS BP have an attractive convergence rate and better error correction performance with low complexity when compared to previous IDS decoders under the white Gaussian noise channel (AWGN).

Modelling and Simulation in Engineering•Jan 19, 2022•4 citations
We propose a reinforcement learning (RL)-based decoding framework for high-throughput parallel decoding of low-density parity-check (LDPC) codes using clustered scheduling. Parallel LDPC decoders must balance error-correction performance and decoding latency while avoiding memory conflicts. To address this trade-off, we construct clusters of check nodes that satisfy a two-edge independence property, which enables conflict-free row-parallel belief propagation. An RL agent is trained offline to assign Q-values to clusters and to prioritize their update order during decoding. To overcome the exponential storage requirements of existing RL-based scheduling methods, we introduce the Q-Sum method, which approximates cluster-level Q-values as the sum of Q-values of individual check nodes, reducing storage complexity from exponential to linear in the number of check nodes. We further propose an On-the-Fly clustering strategy that enforces two-edge independence dynamically during decoding and provides additional flexibility when static clustering is not feasible. Simulation results for array-based LDPC codes over additive white Gaussian noise (AWGN) channels show that the proposed methods improve the latency-versus-performance trade-off of parallel LDPC decoders, achieving lower decoding latency and higher throughput while maintaining error rates comparable to state-of-the-art decoding methods.
Belief-propagation (BP) decoding for quantum low-density parity-check (QLDPC) codes is attractive due to its low complexity and low latency, but it is often limited by short cycles, degeneracy, and convergence failures. Reinforcement-learning-based sequential BP decoding (RL-S) improves BP by learning a syndrome-dependent variable-node (VN) update order, but its VN-by-VN schedule has limited within-iteration parallelism. In this paper, we propose a conflict-free color-clustered extension of RL-S. We construct a VN conflict graph in which two VNs are adjacent if they share an X-type or Z-type check, and color this graph so that same-color VNs have disjoint check neighborhoods. This also prevents VNs from the same Tanner 4- or 6-cycle from being updated simultaneously. During decoding, the trained VN-level Q-table selects a seed VN, and all remaining VNs with the same color are updated in parallel using the same pre-batch messages. For the [[288,12,18]] bivariate-bicycle code over the depolarizing channel, our proposed decoder achieves block-error-rate performance close to VN-level RL-S while reducing the scheduling decisions from 288 VNs to 11 color classes per BP iteration.
Belief-propagation (BP) decoding for quantum low-density parity-check (QLDPC) codes is attractive due to its low complexity, but its performance is often limited by short cycles, degeneracy, and convergence failures. Recently, reinforcement-learning-based sequential variable-node (VN) scheduling (RL-S) was shown to improve BP decoding by learning state-dependent update orders. However, the VN-by-VN nature of that approach offers limited within-iteration parallelism, since only one VN is updated at a time. In this paper, we propose a cluster-based extension of RL-S for QLDPC codes. The VNs are partitioned into fixed clusters, and at each scheduling step the RL agent selects one cluster to update, after which all VNs in that cluster are updated in parallel using the same pre-update incoming messages. To keep the tabular state space practical for large cluster sizes, we introduce a permutation-invariant cluster state based on a normalized histogram of local mismatch weights, followed by quantization. This representation makes the number of cluster states depend on the quantization resolution rather than the cluster size. We also develop the corresponding cluster-level Markov decision process, reward function, and Q-learning update. Numerical results on representative QLDPC codes show that the proposed clustered learned scheduling preserves most of the error-rate benefit of VN-level learned sequential scheduling while substantially reducing the number of scheduling decisions per BP iteration, thereby providing an attractive latency-parallelism tradeoff.
In this work, we consider the decoding of short sparse graph-based channel codes via reinforcement learning (RL). Specifically, we focus on low-density parity-check (LDPC) codes, which for example have been standardized in the context of 5G cellular communication systems due to their excellent error correcting performance. LDPC codes are typically decoded via belief propagation on the corresponding bipartite (Tanner) graph of the code via flooding, i.e., all check and variable nodes in the Tanner graph are updated at once. We model the node-wise sequential LDPC scheduling scheme as a Markov decision process (MDP), and obtain optimized check node (CN) scheduling policies via RL to improve sequential decoding performance as compared to flooding. In each RL step, an agent decides which CN to schedule next by observing a reward associated with each choice. Repeated scheduling enables the agent to discover the optimized CN scheduling policy which is later incorporated in our RL-based sequential LDPC decoder. In order to reduce RL complexity, we propose a novel graph-induced CN clustering approach to partition the state space of the MDP in such a way that dependencies between clusters are minimized. Compared to standard decoding approaches from the literature, some of our proposed RL schemes not only improve the decoding performance, but also reduce the decoding complexity dramatically once the scheduling policy is learned. By concatenating an outer Hamming code with an inner LDPC code which is decoded based on our learned policy, we demonstrate significant improvements in the decoding performance compared to other LDPC decoding policies.
Belief propagation (BP) is attractive for quantum low-density parity-check (QLDPC) decoding because of its low complexity and low latency, but short cycles and degeneracy can limit its error-correction performance. Reinforcement-learned sequential scheduling (RL-S) substantially improves this performance by adapting the variable node (VN) update order, although Q-table storage and heap-based selection introduce additional overhead. We propose bucket RL-S (B-RL-S), which quantizes learned Q-values into integer priorities and schedules VN updates using dynamically maintained first-in, first-out buckets. Without retraining or changing the BP message updates, B-RL-S reduces policy storage and refreshes only priorities affected by local residual syndrome changes. A fixed number of priority levels enables constant-time VN selection and queue relocation. For the [[288,12,18]][[288,12,18]][[288,12,18]] bivariate bicycle code over the depolarizing channel at p=0.05p=0.05p=0.05, B-RL-S with eight priority levels achieves approximately one fifth the block error rate (BLER) of flooding BP followed by order-10 ordered-statistics decoding. The respective caps are 100010001000 sequential iterations for B-RL-S and 100010001000 flooding iterations for the BP stage of the reference decoder. These results highlight strong error correction with inexpensive scheduling and no additional post-processing stage.
Belief-propagation (BP) decoding for quantum low-density parity-check (QLDPC) codes is appealing due to its low complexity, yet it often exhibits convergence issues due to quantum degeneracy and short cycles that exist in the Tanner graph. To overcome this challenge, this paper proposes a reinforcement-learning (RL) approach that learns (offline) how to decode QLDPC codes based on sequential decoding trajectories. The decoding is formulated as a Markov decision process with a local, syndrome-driven state representation of the underlying RL agent. To enable fast inference, critical for practical implementation, we incrementally update our RL-based QLDPC decoder using second-order neighborhoods that avoid global rescans. Simulation results on representative QLDPC codes demonstrate the superiority of the proposed RL-based QLDPC decoders in terms of performance and convergence speed when compared to flooding and random sequential schedules, while achieving performance competitive with state-of-the-art BP-based decoders at comparable complexity.
The informed dynamic scheduling (IDS) strategies for the low-density parity check (LDPC) decoding have shown superior performance in error correction and convergence speed, particularly those based on reliability measures and residual belief propagation (RBP). However, the search for the most unreliable variable nodes and the residual precomputation required for each iteration of the IDS-LDPC increases the complexity of the decoding process which becomes more sequential, making it hard to exploit the parallelism of signal processing algorithms available in multicore platforms. To overcome this problem, a new, low-complexity scheduling system, called layered vicinal variable nodes scheduling (LWNS) is presented in this paper. With this LWNS, each variable node is updated by exchanging intrinsic information with all its associated control and variable nodes before moving to the next variable node updating. The proposed scheduling strategy is fixed by a preprocessing step of the parity control matrix instead of calculation of the residuals values and by computation of the most influential variable node instead the most unreliable metric. It also allows the parallel processing of independent Tanner graph subbranches identified and grouped in layers. Our simulation results show that the LWNS BP have an attractive convergence rate and better error correction performance with low complexity when compared to previous IDS decoders under the white Gaussian noise channel (AWGN).