Federated Learning

Chapter 14: Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond

Zhongxiang Dai^a; Flint Xiaofeng Fan^a; Cheston Tan^c; Trong Nghia Hoang^d; Bryan Kian Hsiang Low^a; Patrick Jaillet^b    aNational University of Singapore, Singapore, Singapore^bMassachusetts Institute of Technology, Cambridge, MA, United States^cInstitute for Infocomm Research, A*STAR, Singapore, Singapore^dWashington State University, Pullman, WA, United States

Abstract

Federated learning (FL) in its classic form involves the collaborative training of supervised learning models (e.g., neural networks) among multiple agents/clients. However, in addition to supervised learning, many other machine learning tasks which are inherently sequential decision-making ...