@article{Hu2023, 
author = {Yuhan Hu and Yawei Zhao and Lailong Luo and Deke Guo},
title = {Boosting for Distributed Online Convex Optimization},
year = {2023},
journal = {Tsinghua Science and Technology},
volume = {28},
number = {4},
pages = {811-821},
keywords = {online boosting, distributed Online Convex Optimization (OCO), Online Gradient Boosting (OGB)},
url = {https://www.sciopen.com/article/10.26599/TST.2022.9010041},
doi = {10.26599/TST.2022.9010041},
abstract = {Decentralized Online Learning (DOL) extends online learning to the domain of distributed networks. However, limitations of local data in decentralized settings lead to a decrease in the accuracy of decisions or models compared to centralized methods. Considering the increasing requirement to achieve a high-precision model or decision with distributed data resources in a network, applying ensemble methods is attempted to achieve a superior model or decision with only transferring gradients or models. A new boosting method, namely Boosting for Distributed Online Convex Optimization (BD-OCO), is designed to realize the application of boosting in distributed scenarios. BD-OCO achieves the regret upper bound  𝒪⁢(M+NM⁢N⁢T), where  M measures the size of the distributed network and  N is the number of Weak Learners (WLs) in each node. The core idea of BD-OCO is to apply the local model to train a strong global one. BD-OCO is evaluated on the basis of eight different real-world datasets. Numerical results show that BD-OCO achieves excellent performance in accuracy and convergence, and is robust to the size of the distributed network.}
}