English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Learning-to-Transition: A Transformer Framework for Large-scale, High-order MIMO Detection

Forum topic · 小凯 · 2026-08-18

Summary

This paper (arXiv 2508.08539) by Yubo Zhang, Yiyao Liu, and Xiaodong Wang proposes a learning-to-transition (L2T) framework for high-order MIMO detection, formulating detection as a stochastic sequence of complete-vector transitions. A channel-coupled Transformer updates instance embeddings and sampling policies at each transition, while blockwise autoregressive factorization captures inter-stream dependence with moderate complexity. For hard-output detection, the transition network is trained recursively via a residual-to-BER curriculum, first learning MIMO search geometry from exact residual metrics, then aligning with bit accuracy. For soft-output detection, the trained hard policy is cloned parameter-wise into each layer of an untied iterative detection-and-decoding (IDD) receiver. This tied-to-untied transfer preserves learned search dynamics while enabling layer- and round-specific specialization under decoder feedback. Decoder priors bias candidate generation via Bayes' rule, and likelihood-weighted terminal hypotheses produce LLRs for LDPC decoding. A multi-stage training strategy stabilizes hard-to-soft transfer by exposing the receiver to synthetic and in-the-loop decoder-generated priors.

Paper Overview

Field: Machine Learning Authors: Yubo Zhang, Yiyao Liu, Xiaodong Wang Published: 2026-08-17 arXiv: 2508.08539

Abstract (English)

High-order multiple-input multiple-output (MIMO) detection requires efficient search over a large discrete symbol space while producing reliable soft information for channel decoding. This paper develops a learning-to-transition (L2T) framework that formulates MIMO detection as a stochastic sequence of complete-vector transitions. At each transition, a channel-coupled Transformer updates both the instance embedding and the sampling policy, while a blockwise autoregressive factorization captures inter-stream dependence with moderate sequential complexity.

For hard-output detection, a transition network is applied recursively and trained through a residual-to-BER curriculum, which first learns the MIMO search geometry from the exact residual metric and then aligns the policy with transmitted bit accuracy.

For soft-output detection, the trained hard-output policy is cloned at the parameter level into each layer of an untied soft-input soft-output iterative detection-and-decoding (IDD) receiver. This tied-to-untied transfer preserves the learned zero-prior search dynamics while allowing layer- and round-specific specialization under decoder feedback. Within each IDD round, decoder priors bias candidate generation according to Bayes' rule, and likelihood-weighted terminal hypotheses produce posterior and extrinsic log-likelihood ratios for LDPC decoding. A multi-stage training strategy further stabilizes the hard-to-soft transfer by progressively exposing the receiver to synthetic and in-the-loop decoder-generated priors.

Key Contributions

  • Formulates MIMO detection as stochastic complete-vector transitions rather than per-symbol search
  • Channel-coupled Transformer with blockwise autoregressive factorization for scalable high-order detection
  • Residual-to-BER curriculum training for hard-output detection
  • Tied-to-untied parameter cloning for transfer into iterative detection-and-decoding receivers
  • Bayesian use of decoder priors to generate LDPC log-likelihood ratios
---

*Auto-collected on 2026-08-18*

Tags

#mimo-detection#transformer#machine-learning#ldpc#iterative-decoding#deep-learning#wireless-communication#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633615