Subsampled model aggregation

Abstract

There has been a recent push for a new framework of learning, due in part to the availability of storage, networking and the abundance of very large datasets. This framework argues for parallelized learning algorithms that can operate on a distributed platform and have the ability to terminate early in the likely event that data size is too inundating. Methods described herein propose a subsampled model aggregation technique based on the bagging algorithm. It is capable of significant run-time reduction with no loss in modeling performance. These claims were validated with a variety of base-learning algorithms on large web and newswire datasets. © World Scientific Publishing Company.