# Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems

arXiv: https://arxiv.org/abs/2605.14331 · HTML: https://mlsanity.com/paper/2605.14331/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Federated Learning via Over-the-Air Computation](https://mlsanity.com/paper/1812.11750/) (2018)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing Systems](https://mlsanity.com/paper/2005.02459/) (2020)
- [Task-Oriented Over-the-Air Computation for Multi-Device Edge AI](https://mlsanity.com/paper/2211.01255/) (2022)
- [Dynamic Precision Analog Computing for Neural Networks](https://mlsanity.com/paper/2102.06365/) (2021)
- [Integrated Sensing, Communication, and Computation Over-the-Air: MIMO Beamforming Design](https://mlsanity.com/paper/2201.12581/) (2022)
- [Parallel and Distributed Methods for Nonconvex Optimization--Part II: Applications](https://mlsanity.com/paper/1601.04059/) (2016)
- [Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2508.01840/) (2025)
- [Multiple Access Techniques for Intelligent and Multi-Functional 6G: Tutorial, Survey, and Outlook](https://mlsanity.com/paper/2401.01433/) (2024)
- [Analog Computing for Signal Processing and Communications -- Part I: Computing with Microwave Networks](https://mlsanity.com/paper/2504.06790/) (2025)
- [Analog Computing for Signal Processing and Communications -- Part II: Toward Gigantic MIMO Beamforming](https://mlsanity.com/paper/2504.07477/) (2025)
- [MIMO Systems Aided by Microwave Linear Analog Computers: Capacity-Achieving Architectures with Reduced Circuit Complexity](https://mlsanity.com/paper/2506.15052/) (2025)
- [Multimodal Mixture-of-Experts for ISAC in Low-Altitude Wireless Networks](https://mlsanity.com/paper/2512.01750/) (2025)
- [RF-Transformer: A Unified Backscatter Radio Hardware Abstraction](https://mlsanity.com/paper/2209.15195/) (2022)

## Abstract (arXiv)

Modern edge devices increasingly rely on neural networks for intelligent applications. However, conventional digital computing-based edge inference requires substantial memory and energy consumption. In analog radio frequency (RF) computing, a base station (BS) encodes the weights of the neural networks and broadcasts the RF waveforms to the clients. Each client reuses its passive mixer to multiply the received weight-encoded waveform with a locally generated input-encoded waveform. This enables wireless receivers to perform the matrix-vector multiplications (MVMs) that account for most of the computation burden in edge inference with ultra-low energy consumption. Unlike conventional downlink transmissions which are optimized for communications, analog RF computing requires a computing-centric physical layer that controls both the analog MVM accuracy and the energy consumption for inference. Motivated by this, in this paper, we propose a physical layer design framework for analog RF computing in MU-MIMO wireless systems. We derive tractable models for computing accuracy and energy consumption for inference, formulate a joint BS beamforming and client-side scaling problem subject to computing accuracy, transmit power, and hardware constraints, and develop a low-complexity algorithm to solve the non-convex problem. The proposed design provides client- and layer-specific accuracy control for both uniform- and mixed-precision inference. Simulations under 3GPP specifications show that analog RF computing can significantly reduce client-side energy consumption by nearly two orders of magnitude compared to digital computing, while mixed-precision inference requires even lower energy consumption than uniform-precision inference. Overall, these results establish analog RF computing over wireless networks as a promising paradigm for energy-efficient edge inference.