Large-Scale Sparse Subspace Clustering Using Landmarks
This work addresses scalability issues in unsupervised learning for large datasets, though it appears incremental as it builds on existing subspace clustering methods.
The paper tackles the high computational complexity of subspace clustering on large-scale datasets by introducing an efficient approach using landmarks, achieving linear time complexity with respect to data size.
Subspace clustering methods based on expressing each data point as a linear combination of all other points in a dataset are popular unsupervised learning techniques. However, existing methods incur high computational complexity on large-scale datasets as they require solving an expensive optimization problem and performing spectral clustering on large affinity matrices. This paper presents an efficient approach to subspace clustering by selecting a small subset of the input data called landmarks. The resulting subspace clustering method in the reduced domain runs in linear time with respect to the size of the original data. Numerical experiments on synthetic and real data demonstrate the effectiveness of our method.