Turbo-ICL: In-Context Learning-Based Turbo Equalization

TL;DR

This paper proposes a novel in-context learning framework for turbo equalization in MIMO systems, leveraging prompt augmentation and Transformer or state-space models to outperform traditional methods especially in challenging scenarios.

Contribution

It introduces a new ICL-based turbo equalization approach with prompt augmentation, and develops Transformer and state-space model variants for improved performance.

Findings

ICL equalizers outperform traditional baselines in low-resolution quantization scenarios.

Transformer models excel with limited training diversity.

State-space models are efficient in resource-constrained environments.

Abstract

This paper introduces a novel in-context learning (ICL) framework, inspired by large language models (LLMs), for soft-input soft-output channel equalization in coded multiple-input multiple-output (MIMO) systems. The proposed approach learns to infer posterior symbol distributions directly from a prompt of pilot signals and decoder feedback. A key innovation is the use of prompt augmentation to incorporate extrinsic information from the decoder output as additional context, enabling the ICL model to refine its symbol estimates iteratively across turbo decoding iterations. Two model variants, based on Transformer and state-space architectures, are developed and evaluated. Extensive simulations demonstrate that, when traditional linear assumptions break down, e.g., in the presence of low-resolution quantization, ICL equalizers consistently outperform conventional model-based baselines, even when the latter are provided with perfect channel state information. Results also highlight the advantage of Transformer-based models under limited training diversity, as well as the efficiency of state-space models in resource-constrained scenarios.