Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems

2026-04-23

AI Summary

This work addresses the challenge of achieving high-accuracy MIMO channel state information (CSI) estimation under stringent low-latency constraints by proposing a nullspace flow matching framework. The approach decomposes CSI into a signal subspace component that can be directly recovered and a nullspace component that requires modeling, applying flow matching only to the latter for efficient generative optimization. By integrating a power-law time scheduling scheme and a noise-aware adaptive correction strategy, the method substantially enhances both inference efficiency and estimation accuracy within a strict latency budget of approximately 3 milliseconds. Experimental results demonstrate that the proposed framework outperforms existing model-based and generative baselines in terms of normalized mean squared error (NMSE), effectively balancing real-time performance with estimation fidelity.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. While advanced deep generative models, such as score-based and diffusion models, enable high-fidelity CSI reconstruction from limited pilot observations, they often suffer from high inference latency. To achieve accurate CSI estimation under stringent latency constraints, this paper proposes a null-space flow matching (FM) framework that decomposes pilot-limited MIMO channel estimation into a range-space reconstruction problem and a null-space generation problem. Specifically, the range-space component of the channel is directly recovered from noisy pilot observations, while only the ambiguous null-space component is iteratively refined using an FM-based generative prior. To further improve the robustness of the proposed framework, we introduce a power-law time schedule to better allocate the limited number of refinement steps, along with a noise-aware adaptive correction strategy to suppress channel noise on the refinement trajectory. Experimental results demonstrate that our method achieves a competitive normalized mean square error (NMSE) even under a strict latency budget of around 3 ms, while delivering superior estimation accuracy and faster inference than both model-based and generative baselines.

Problem

• MIMO channel estimation
• latency-constrained systems
• channel state information
• low-latency inference
• pilot-limited CSI acquisition

Innovation

• null-space flow matching
• MIMO channel estimation
• latency-constrained inference
• generative prior
• power-law time schedule