When to Stop? Dynamic Early Termination of Sequential Ensembles
Abstract
Ordered-statistics decoding (OSD) post-processing substantially improves the performance of belief propagation (BP) ensembles, but it also removes their natural syndrome-based stopping criterion. The high computational complexity of ensemble decoding and OSD can be reduced by sequential activation of ensemble members paired with an early termination. Instead of a syndrome-based termination we therefore apply dynamic ensemble termination (DET) to sequential ensembles: members are evaluated one at a time and decoding stops when the estimated risk that an unseen member would correct the current decision falls below an offline-fitted threshold. With hardware-oriented design in mind, we instantiate the framework with layered normalized min-sum component decoders, a row-boosted ensemble, conditional low-order OSD on the dual code, and a conventional low-cost decoder gate. A decision tree estimates the residual risk from statistics of the current candidate list. Member-dependent thresholds then target a prescribed frame error rate (FER) loss. We validate this framework on mutliple IEEE 802.11 low-density parity-check (LDPC) codes with blocklengths 648,1296, and 1944 at rates 1/2 and 5/6. At each code's design point, where the full 64-member list reaches an FER of 10−3, the DET decoder processes 1.04 to 1.15 members on average. On the (648,540) code, it reduces BP work by 39× and OSD activations by 18× against the full list while retaining an signal-to-noise ratio (SNR) gain of about 0.4 dB.
Related
- When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments
- Theoretical Foundations of Sequential Dynamic Programming
- Regularized Sequential Reconstructions of Dynamic Nonsmooth Sources from Sparse Boundary Flux Data
- Sequential Automorphism Ensemble Decoding with Early Stopping
- Sequential State-Dependent Kalman Filtering for Dynamic Parameter Estimation of a Mobile User in a Large Cellular Network
BibTeX
@misc{bezner2026when,
title = {{When to Stop? Dynamic Early Termination of Sequential Ensembles}},
author = {Paul Bezner and Felix Krieg and Stephan ten Brink},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.26215},
eprint = {2609.26215},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.26215},
}
RIS
TY - UNPB
TI - When to Stop? Dynamic Early Termination of Sequential Ensembles
AU - Paul Bezner
AU - Felix Krieg
AU - Stephan ten Brink
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.26215
UR - https://arxiv.org/abs/2609.26215
AB - Ordered-statistics decoding (OSD) post-processing substantially improves the performance of belief propagation (BP) ensembles, but it also removes their natural syndrome-based stopping criterion. The high computational complexity of ensemble decoding and OSD can be reduced by sequential activation of ensemble members paired with an early termination. Instead of a syndrome-based termination we therefore apply dynamic ensemble termination (DET) to sequential ensembles: members are evaluated one at a time and decoding stops when the estimated risk that an unseen member would correct the current decision falls below an offline-fitted threshold. With hardware-oriented design in mind, we instantiate the framework with layered normalized min-sum component decoders, a row-boosted ensemble, conditional low-order OSD on the dual code, and a conventional low-cost decoder gate. A decision tree estimates the residual risk from statistics of the current candidate list. Member-dependent thresholds then target a prescribed frame error rate (FER) loss. We validate this framework on mutliple IEEE 802.11 low-density parity-check (LDPC) codes with blocklengths 648,1296, and 1944 at rates 1/2 and 5/6. At each code's design point, where the full 64-member list reaches an FER of 10^−3, the DET decoder processes 1.04 to 1.15 members on average. On the (648,540) code, it reduces BP work by 39× and OSD activations by 18× against the full list while retaining an signal-to-noise ratio (SNR) gain of about 0.4 dB.
ER -