RWTH Aachen University
In this paper, the authors present the first protocol for distributed online prediction that aims to minimize online prediction loss and net-work communication at the same time. Applications include social content recommendation, algorithmic trading, and other scenarios where a configuration of local prediction models of high-frequency streams is used to provide a real-time service. For stationary data, the proposed protocol retains the asymptotic optimal regret of previous algorithms. At the same time, it allows to substantially reducing network communication, and, in contrast to previous approaches, it remains applicable when the data is non-stationary and shows rapid concept drift.