arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12733cs.LG
收藏

多核分布式在线学习

Distributed Online Learning with Multiple Kernels

University of Southern California(南加州大学);Hanyang University(汉阳大学)

Jeongmin Chae, Songnam Hong

摘要:

我们考虑的问题,学习一个非线性函数在一个网络的学习者在一个完全分散的方式。另外假设在线学习,其中每个学习者在本地接收连续流数据。这种学习模型被称为完全分布式在线学习(或完全分散式在线联邦学习)。针对该模型,我们提出了一种新的多核学习框架,称为DOMKL。建议的DOMKL是通过利用在线交替方向法的乘数和分布式对冲算法的原则。我们从理论上证明了DOMKL在T个时隙上可以实现最佳的次线性遗憾,这意味着网络中的每个学习者都可以学习一个共同的函数,该函数与事后的最佳函数之间的差距越来越小。我们的分析还表明,DOMKL产生了与最先进的集中式方法相同的渐近性能,同时保持边缘学习器的本地数据。通过对真实数据集的数值测试,我们证明了所提出的DOMKL在各种在线回归和时间序列预测任务上的有效性。

英文摘要:

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, implying that every learner in the network can learn a common function which has a diminishing gap from the best function in hindsight. Our analysis also reveals that DOMKL yields the same asymptotic performance of 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑