.png){kind=icon}
.png){kind=icon}
Return
Distributed Online Learning With Multiple Kernels
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2021.3105146.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We consider the problem of learning a nonlinear function over a network of learners in a fully decentralized fashion Online learning is additionally assumed where every learner receives continuous streaming data locally This learning model is called a fully distributed online learning or a fully decentralized online federated learning). For this model, we propose a novel learning framework with multiple kernels, which is named DOMKL. The proposed DOMKL is devised by harnessing the principles of an online alternating direction method of multipliers and a distributed Hedge algorithm. We theoretically prove that DOMKL over T time slots can achieve an optimal sublinear regret O(root T), implying that every learner in the network can learn a common function having a diminishing gap from the best function in hindsight. Our analysis also reveals that DOMKL yields the same asymptotic performance as the state-of-the-art centralized approach while keeping local data at edge learners. Via numerical tests with real datasets, we demonstrate the effectiveness of the proposed DOMKL on various online regression and time-series prediction tasks.
Keywords:
Kernel
Task analysis
Optimization
Distributed databases
Distance learning
Dictionaries
Computer aided instruction
Decentralized federated learning
distributed online learning
multiple kernel learning (MKL)
online learning
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W