Clustering High-Dimensional Data via Random Sampling and Consensus

In response to the urgent need for learning tools tuned to big data analytics, the present paper introduces a feature selection approach to efficient clustering of high-dimensional vectors. The resultant method leverages random sampling and consensus (RANSAC) arguments, originally developed for robust regression tasks in computer vision, to yield novel dimensionality reduction schemes. The advocated random sampling and consensus K-means (RSC-Kmeans) algorithm can operate in either batch or sequential modes, with the latter being able to afford lower computational footprint than the former. Extensive numerical tests on synthetic and real datasets highlight the potential of the proposed algorithms, and demonstrate their competitive performance relative to state-of-the-art random projection alternatives.