Fusing Multiple Algorithms for Heterogeneous Online Learning

This paper addresses the challenge of online learning in contexts where agents accumulate disparate data and use different local learning algorithms due to resource constraints. We introduce the Switched Online Learning Algorithm (SOLA), designed to solve the heterogeneous online learning problem by fusing updates from diverse agents through a dynamic switching mechanism contingent upon their respective performance and available resources. We theoretically analyze the design of the selecting mechanism to ensure that the regret of SOLA is bounded. Our findings show that the number of changes in selection needs to be bounded by a parameter dependent on the performance of the different local algorithms. Additionally, two numerical experiments are presented to emphasize the effectiveness of SOLA, first on an online linear regression problem and then on an online classification problem with the MNIST dataset.