# Collaborative Machine Learning at the Wireless Edge with Blind Transmitters

arXiv: https://arxiv.org/abs/1907.03909 · HTML: https://mlsanity.com/paper/1907.03909/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [Federated Edge Learning with Misaligned Over-The-Air Computation](https://mlsanity.com/paper/2102.13604/) (2021)
- [Joint Optimization of Communications and Federated Learning Over the Air](https://mlsanity.com/paper/2104.03490/) (2021)
- [Accelerated Gradient Descent Learning over Multiple Access Fading Channels](https://mlsanity.com/paper/2107.12452/) (2021)
- [1-Bit Compressive Sensing for Efficient Federated Learning Over the Air](https://mlsanity.com/paper/2103.16055/) (2021)
- [Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learning](https://mlsanity.com/paper/2210.07012/) (2022)
- [BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackers](https://mlsanity.com/paper/2110.09660/) (2021)
- [Fundamental limits of over-the-air optimization: Are analog schemes optimal?](https://mlsanity.com/paper/2109.05222/) (2021)

## Abstract (arXiv)

We study wireless collaborative machine learning (ML), where mobile edge devices, each with its own dataset, carry out distributed stochastic gradient descent (DSGD) over-the-air with the help of a wireless access point acting as the parameter server (PS). At each iteration of the DSGD algorithm wireless devices compute gradient estimates with their local datasets, and send them to the PS over a wireless fading multiple access channel (MAC). Motivated by the additive nature of the wireless MAC, we propose an analog DSGD scheme, in which the devices transmit scaled versions of their gradient estimates in an uncoded fashion. We assume that the channel state information (CSI) is available only at the PS. We instead allow the PS to employ multiple antennas to alleviate the destructive fading effect, which cannot be cancelled by the transmitters due to the lack of CSI. Theoretical analysis indicates that, with the proposed DSGD scheme, increasing the number of PS antennas mitigates the fading effect, and, in the limit, the effects of fading and noise disappear, and the PS receives aligned signals used to update the model parameter. The theoretical results are then corroborated with the experimental ones.