Distributed learning algorithm for feedforward neural networks

With the appearance of huge data sets new challenges have risen regarding the scalability and efficiency of Machine Learning algorithms, and both distributed computing and randomized algorithms have become effective ways to handle them. Taking advantage of these two approaches, a distributed learning algorithm for two-layer neural networks is proposed. Results demonstrate a similar accuracy when compared to an equivalent non-distributed approach whilst providing some advantages that make it especially well-suited for Big Data sets: over 50% savings in computational time; low communication and storage cost; no hyperparameters to be tuned; it allows online learning and it is privacy-preserving.