MLFeb 16, 2015

Random Subspace Learning Approach to High-Dimensional Outliers Detection

arXiv:1502.04416v51 citations
AI Analysis

This work addresses outlier detection for high-dimensional data, offering a computationally efficient solution that is incremental in nature.

The authors tackled the problem of outlier detection in high-dimensional datasets by introducing a random subspace learning approach, which achieved computational efficiency and competitive detection accuracy compared to existing methods.

We introduce and develop a novel approach to outlier detection based on adaptation of random subspace learning. Our proposed method handles both high-dimension low-sample size and traditional low-dimensional high-sample size datasets. Essentially, we avoid the computational bottleneck of techniques like minimum covariance determinant (MCD) by computing the needed determinants and associated measures in much lower dimensional subspaces. Both theoretical and computational development of our approach reveal that it is computationally more efficient than the regularized methods in high-dimensional low-sample size, and often competes favorably with existing methods as far as the percentage of correct outlier detection is concerned.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes