Universal Approximation with XL MIMO Systems: OTA Classification via Trainable Analog Combining

2025-04-17

AI Summary

This work addresses the challenge of deploying conventional digital neural network inference on ultra-low-power wireless edge devices. We propose a novel over-the-air (OTA) edge inference paradigm leveraging extra-large-scale MIMO (XL-MIMO). Our key innovation is the first formulation of the XL-MIMO channel response as a fixed random hidden layer, with a trainable analog combiner serving as the output layer—yielding a physical-layer-native “Air-Extreme Learning Machine” (Air-ELM). This approach entirely bypasses digital baseband processing and transmitter-side precoding, enabling zero preprocessing and near-instantaneous end-to-end analog-domain inference. Experiments demonstrate that Air-ELM achieves classification accuracy comparable to deep learning and classical ELM, while reducing computational complexity by two to three orders of magnitude. Consequently, it significantly enhances real-time edge intelligence capabilities for ultra-low-power devices.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Humans and AI: Human-in-the-loop Machine Learning
• Search and Optimization: Learning to Search

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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In this paper, we demonstrate that an eXtremely Large (XL) Multiple-Input Multiple-Output (MIMO) wireless system with appropriate analog combining components exhibits the properties of a universal function approximator, similar to a feedforward neural network. By treating the XL MIMO channel coefficients as the random nodes of a hidden layer, and the receiver's analog combiner as a trainable output layer, we cast the end-to-end system to the Extreme Learning Machine (ELM) framework, leading to a novel formulation for Over-The-Air (OTA) edge inference without requiring traditional digital processing nor pre-processing at the transmitter. Through theoretical analysis and numerical evaluation, we showcase that XL-MIMO-ELM enables near-instantaneous training and efficient classification, suggesting the paradigm shift of beyond massive MIMO systems as neural networks alongside their profound communications role. Compared to deep learning approaches and conventional ELMs, the proposed framework achieves on par performance with orders of magnitude lower complexity, making it highly attractive for ultra low power wireless devices.

Problem

• XL MIMO systems as universal function approximators
• OTA edge inference without digital processing
• Low complexity classification for wireless devices

Innovation

• XL MIMO as universal function approximator
• Trainable analog combiner for OTA inference
• Extreme Learning Machine with low complexity