Harnessing Bandit Online Learning to Low-Latency Fog Computing

This paper focuses on the online fog computing tasks in the Internet-of-Things (IoT), where online decisions must flexibly adapt to the changing user preferences (loss functions), and the temporally unpredictable availability of resources (constraints). Tailored for such human-in-the-loop systems where the loss functions are hard to model, a family of bandit online saddle-point (BanSP) schemes are developed, which adaptively adjust the online operations based on (possibly multiple) bandit feedback of the loss functions, and the changing environment. Performance here is assessed by: i) dynamic regret that generalizes the widely used static regret; and, ii) fit that captures the accumulated amount of constraint violations. Specifically, BanSP is proved to simultaneously yield sub-linear dynamic regret and fit, provided that the best dynamic solutions vary slowly over time. Numerical tests on fog computing tasks corroborate that BanSP offers desired performance under such limited information.