Large-scale subspace clustering using random sketching and validation

While successful in clustering multiple types of high-dimensional data, subspace clustering algorithms do not scale well as the number of data increases. The present paper puts forth a novel randomized subspace clustering algorithm for high-dimensional data based on a random sketching and validation approach. Utilizing a data-driven random sketching technique to estimate the underlying probability density function of the data, the performance of the proposed method is assessed via simulations, and is compared with state-of-the-art sparse subspace clustering methods.