Machine Intelligence on Wireless Edge Networks

TL;DR

This paper proposes a novel wireless edge inference method where model weights are broadcast via RF signals, enabling local computation on existing radio hardware, reducing energy and latency compared to traditional cloud-based approaches.

Contribution

Introducing a hardware-aware wireless inference framework that leverages existing RF components for local model inference, reducing hardware complexity and communication costs.

Findings

RF-based inference achieves high accuracy with reduced hardware overhead

Thermal noise and nonlinearity define an optimal energy window for analog computation

Simulations confirm reduced memory and conversion overhead while maintaining accuracy

Abstract

Machine intelligence on edge devices enables low-latency processing and improved privacy, but is often limited by the energy and delay of moving and converting data. Current systems frequently avoid local model storage by sending queries to a server, incurring uplink cost, network latency, and privacy risk. We present the opposite approach: broadcasting model weights to clients that perform inference locally using in-physics computation inside the radio receive chain. A base station transmits weights as radio frequency (RF) waveforms; the client encodes activations onto the waveform and computes the result using existing mixer and filter stages, RF components already present in billions of edge devices such as cellphones, eliminating repeated signal conversions and extra hardware. Analysis shows that thermal noise and nonlinearity create an optimal energy window for accurate analog inner products. Hardware-tailored training through a differentiable RF chain preserves accuracy within this regime. Circuit-informed simulations, consistent with a companion experiment, demonstrate reduced memory and conversion overhead while maintaining high accuracy in realistic wireless edge scenarios.