CSI Feedback Under Basis Mismatch: Rate-Splitting Transform Coding for FDD Massive MIMO

2026-04-22

AI Summary

This work addresses the performance degradation in CSI feedback for FDD massive MIMO systems caused by mismatch between the transmitter and receiver bases. To mitigate this issue, the authors propose a practical feedback architecture that decouples long-term basis and short-term coefficient quantization, combined with stochastic vector quantization for efficient compression. They derive, for the first time, a closed-form expression for the end-to-end mean squared error, which reveals the optimal bit allocation strategy and uncovers a phase-transition threshold governing basis update necessity. The proposed method integrates Karhunen–Loève transform, reverse water-filling power allocation, and rate-splitting coding, achieving near rate-distortion bounds under both Gaussian and COST2100 channels. It significantly outperforms deep learning-based autoencoder approaches while exhibiting lower computational complexity and greater robustness to basis update overhead.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Learning & Optimization for CV

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In frequency division duplex massive multiple-input multiple-output systems, downlink channel state information must be fed back within a limited uplink budget. While transform coding with Karhunen-Loeve transform and reverse water-filling is rate-distortion optimal for Gaussian channels, its performance is limited by basis mismatch between the user and base station. We analyze this mismatch and propose a practical architecture separating long-term basis feedback from short-term coefficient quantization. Using a random vector quantization, we derive a closed-form end-to-end mean square error expression. This allows us to characterize the optimal rate split and identify a phase transition threshold for basis updates. Simulations on correlated Gaussian and COST2100 channels demonstrate near-optimal performance, robustness to update overhead, and significant complexity reduction compared to deep-learning-based autoencoders.

Problem

• CSI feedback
• basis mismatch
• FDD massive MIMO
• transform coding
• channel state information

Innovation

• Rate-Splitting
• Basis Mismatch
• Transform Coding
• Random Vector Quantization
• Massive MIMO