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*