Optimized Power Control Design for Over-the-Air Federated Edge Learning
arXiv:2106.09316
Abstract
This paper investigates the transmission power control in over-the-air federated edge learning (Air-FEEL) system. Different from conventional power control designs (e.g., to minimize the individual mean squared error (MSE) of the over-the-air aggregation at each round), we consider a new power control design aiming at directly maximizing the convergence speed. Towards this end, we first analyze the convergence behavior of Air-FEEL (in terms of the optimality gap) subject to aggregation errors at different communication rounds. It is revealed that if the aggregation estimates are unbiased, then the training algorithm would converge exactly to the optimal point with mild conditions; while if they are biased, then the algorithm would converge with an error floor determined by the accumulated estimate bias over communication rounds. Next, building upon the convergence results, we optimize the power control to directly minimize the derived optimality gaps under both biased and unbiased aggregations, subject to a set of average and maximum power constraints at individual edge devices. We transform both problems into convex forms, and obtain their structured optimal solutions, both appearing in a form of regularized channel inversion, by using the Lagrangian duality method. Finally, numerical results show that the proposed power control policies achieve significantly faster convergence for Air-FEEL, as compared with benchmark policies with fixed power transmission or conventional MSE minimization.
arXiv commentThis paper is an extension of a conference paper and to appear in IEEE JSAC
References in corpus (11)
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Strategies for Improving Communication Efficiency
- Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
- On Analog Gradient Descent Learning over Multiple Access Fading Channels
- Joint Optimization of Communications and Federated Learning Over the Air
- Edge Federated Learning Via Unit-Modulus Over-The-Air Computation
- Learning Rate Optimization for Federated Learning Exploiting Over-the-air Computation
- Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints
- Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints
- 1-Bit Compressive Sensing for Efficient Federated Learning Over the Air
- Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach