BriefGPT.xyz
Jun, 2022
基于核的上下文臂机的通讯高效分布式学习
Communication Efficient Distributed Learning for Kernelized Contextual Bandits
HTML
PDF
Chuanhao Li, Huazheng Wang, Mengdi Wang, Hongning Wang
TL;DR
本文针对分布式学习环境下学习核化上下文赌博机问题的通信效率挑战,提出了一种基于Nyström嵌入的解决方案,可以在保证通信效率的同时,实现对非线性映射的学习。通过严谨的证明,证明了该算法在遗憾和通信成本方面可以获得次线性速率。
Abstract
We tackle the
communication efficiency
challenge of learning kernelized
contextual bandits
in a distributed setting. Despite the recent advances in communication-efficient distributed bandit learning, existing so
→