Ensemble Gaussian Processes for Online Learning with Application to IoT, Part 1 of 2

Internet-of-Things (IoT) offers an intelligent infrastructure of networked smart devices offering task-specific monitoring and control services. IoT?s unique features include heterogeneity, ubiquitous low-power devices, and unpredictable dynamics also due to human participation. The need naturally arises for foundational innovations in network monitoring and management to allow efficient adaptation to changing environments, and low-cost service provisioning, subject to stringent latency constraints. To this end, the overarching theme of this tutorial is a unifying framework for online monitoring and management for IoT through contemporary communication, networking, learning, and optimization advances. From the network architecture vantage point, the unified framework leverages a promising architecture termed fog that enables smart devices to have proximity access to cloud functionalities at the network edge, along the cloud-to-things continuum. From the algorithmic perspective, key innovations include online approaches based on ensemble Gaussian processes that can offer adaptivity to different degrees of nonstationary in IoT dynamics. Scalability of implementation further motivates bandit operation along with local information exchanges that enable distributed approaches. The outlined framework can serve as a stepping stone that leads to systematic designs and rigorous analysis of task-specific learning and management schemes for IoT.