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

2024-04-22

IEEE Communications Letters

AI Summary

Short LDPC codes exhibit residual errors under normalized min-sum (NMS) decoding, while conventional ordered statistics decoding (OSD) achieves high error-correction performance at prohibitively high computational complexity—rendering it unsuitable for ultra-low-latency applications. To address this trade-off, we propose a lightweight neural-enhanced OSD framework. Our method introduces: (i) a sliding-window-assisted neural network to enable early termination of OSD iterations; (ii) a bit-reliability refinement mechanism leveraging iterative failure information; and (iii) a structured, block-wise test-error pattern generation strategy. Evaluated on standardized short LDPC codes, the proposed decoder attains state-of-the-art (SOTA) bit-error-rate (BER) performance—matching or surpassing conventional OSD—while reducing average decoding latency by up to 62% and computational complexity by over 50%. The approach is particularly well-suited for ultra-reliable low-latency communication (URLLC) systems, such as those in 5G and beyond.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Hardware-aware ML
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• Reducing computational complexity in ordered statistics decoding
• Improving decoding performance for short LDPC codes
• Balancing latency and accuracy with neural networks

Innovation

• Neural network refines codeword bit measurement
• Fixed decoding path with test error patterns
• Sliding window enables early termination