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

2025-12-20

AI Summary

Addressing the challenge of balancing decoding performance and computational complexity in low-latency quantum error correction (≤5 iterations), this paper proposes a trainable-weight evolutionary belief propagation (EBP) decoder jointly optimized with ordered statistics decoding (OSD). We introduce differential evolution—a global optimization algorithm—into end-to-end BP weight learning for the first time, enabling co-training of EBP and OSD to significantly enhance generalization and noise robustness under extremely limited iterations. The framework uniformly supports both surface codes and quantum LDPC codes. Within five iterations, it achieves higher logical error correction success rates and lower computational overhead compared to conventional BP+OSD. This work establishes an efficient, scalable, and practical decoding paradigm for fault-tolerant quantum computing.

Technology Category

Machine Learning: Quantum Machine LearningSearch and Optimization: Evolutionary ComputationConstraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystemsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingGraph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

We propose an evolutionary belief propagation (EBP) decoder for quantum error correction, which incorporates trainable weights into the BP algorithm and optimizes them via the differential evolution algorithm. This approach enables end-to-end optimization of the EBP combined with ordered statistics decoding (OSD). Experimental results on surface codes and quantum low-density parity-check codes show that EBP+OSD achieves better decoding performance and lower computational complexity than BP+OSD, particularly under strict low latency constraints (within 5 BP iterations).

Problem

• Optimizing quantum error correction decoding performance
• Reducing computational complexity in low-latency constraints
• Enhancing surface and quantum LDPC codes decoding efficiency

Innovation

• Evolutionary BP with trainable weights optimization
• Combined with ordered statistics decoding for efficiency
• Low-latency decoding within five BP iterations