Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Akyildiz, Talha, Mahdavifar, Hessam
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.20385
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918400383516672
author Akyildiz, Talha
Mahdavifar, Hessam
author_facet Akyildiz, Talha
Mahdavifar, Hessam
contents Local constraint ordered statistics decoding (LC-OSD) provides strong soft decision performance for short block length linear codes, but its practical cost is dominated by the number of tested error patterns (TEPs). This paper proposes a neural early stopping (NES) protocol for LC-OSD with explicit cost control through one trade-off parameter balancing frame error risk and search effort. The proposed approach is trained with frame error rate (FER)-aligned supervision at predefined checkpoints, and learns if additional search is still likely to improve the current best candidate. Later, stopping is decided by comparing predicted continuation need with a cost measured in TEPs. Experimental results across multiple code families show that the proposed protocol significantly reduces average TEP count with only marginal FER degradation, using a single global model for the range of all operating signal-to-noise ratios (SNRs).
format Preprint
id arxiv_https___arxiv_org_abs_2603_20385
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cost-Aware Neural Early Stopping for Local Constraint OSD Decoders
Akyildiz, Talha
Mahdavifar, Hessam
Signal Processing
Local constraint ordered statistics decoding (LC-OSD) provides strong soft decision performance for short block length linear codes, but its practical cost is dominated by the number of tested error patterns (TEPs). This paper proposes a neural early stopping (NES) protocol for LC-OSD with explicit cost control through one trade-off parameter balancing frame error risk and search effort. The proposed approach is trained with frame error rate (FER)-aligned supervision at predefined checkpoints, and learns if additional search is still likely to improve the current best candidate. Later, stopping is decided by comparing predicted continuation need with a cost measured in TEPs. Experimental results across multiple code families show that the proposed protocol significantly reduces average TEP count with only marginal FER degradation, using a single global model for the range of all operating signal-to-noise ratios (SNRs).
title Cost-Aware Neural Early Stopping for Local Constraint OSD Decoders
topic Signal Processing
url https://arxiv.org/abs/2603.20385