Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building

The popularity of sensors and IoT devices has the potential of generating and equivalently accumulating data in order of Zeta bytes [1] annually. High throughput, low latency, data consumption, networking dependencies are often the key metrics in designing high-performance learning algorithms under the constraint of low powered computing. In recent times, there has been an alternate trend to process data on cloud or dump into a centralized database. Commonly known as edge computing, the new paradigm embraces the idea of using interconnected computing nodes to reduce high bandwidth consuming data uploads, privacy preservation of data and knowledge on the fly. Smart building applications typically have a profound implication on environment in terms of energy savings, reduction of green house emission, etc. Predicting the future often forms the basis of corrective actions taken by such apps and can be regarded as a predominant use-case of machine learning.