English

Decentralized Federated Learning via Non-Coherent Over-the-Air Consensus

Information Theory 2023-02-06 v2 Signal Processing math.IT

Abstract

This paper presents NCOTA-DGD, a Decentralized Gradient Descent (DGD) algorithm that combines local gradient descent with a novel Non-Coherent Over-The-Air (NCOTA) consensus scheme to solve distributed machine-learning problems over wirelessly-connected systems. NCOTA-DGD leverages the waveform superposition properties of the wireless channels: it enables simultaneous transmissions under half-duplex constraints, by mapping local optimization signals to a mixture of preamble sequences, and consensus via non-coherent combining at the receivers. NCOTA-DGD operates without channel state information at transmitters and receivers, and leverages the average channel pathloss to mix signals, without explicit knowledge of the mixing weights (typically known in consensus-based optimization algorithms). It is shown both theoretically and numerically that, for smooth and strongly-convex problems with fixed consensus and learning stepsizes, the updates of NCOTA-DGD converge in Euclidean distance to the global optimum with rate O(K1/4)\mathcal O(K^{-1/4}) for a target of KK iterations. NCOTA-DGD is evaluated numerically over a logistic regression problem, showing faster convergence vis-\`a-vis running time than implementations of the classical DGD algorithm over digital and analog orthogonal channels.

Keywords

Cite

@article{arxiv.2210.15806,
  title  = {Decentralized Federated Learning via Non-Coherent Over-the-Air Consensus},
  author = {Nicolò Michelusi},
  journal= {arXiv preprint arXiv:2210.15806},
  year   = {2023}
}

Comments

To appear at IEEE ICC 2023