Optimal Batch Allocation for Wireless Federated Learning

arXiv:2404.02395v1 Announce Type: new
Abstract: Federated learning aims to construct a global model that fits the dataset distributed across local devices without direct access to private data, leveraging communication between a server and the local devices. In the context of a practical communication scheme, we study the completion time required to achieve a target performance. Specifically, we analyze the number of iterations required for federated learning to reach a specific optimality gap from a minimum global loss. Subsequently, we characterize …

abstract arxiv communication construct context cs.dc cs.lg data dataset devices distributed federated learning global practical private data server study type wireless