Fusing Multiple Algorithms for Heterogeneous Online Learning
This addresses the problem of coordinating diverse algorithms in distributed online learning systems, though it appears incremental as it builds on existing switching mechanisms.
This paper tackles the challenge of heterogeneous online learning where agents use different algorithms under resource constraints by introducing the Switched Online Learning Algorithm (SOLA), which dynamically switches between agents based on performance and resources to achieve bounded regret.
This study addresses the challenge of online learning in contexts where agents accumulate disparate data, face resource constraints, and use different local algorithms. This paper introduces the Switched Online Learning Algorithm (SOLA), designed to solve the heterogeneous online learning problem by amalgamating 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 test cases 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.