Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering
Chong You, Chun-Guang Li, Daniel P. Robinson, Rene Vidal

TL;DR
This paper introduces a scalable active set algorithm for elastic net subspace clustering, balancing connectivity and subspace preservation, and demonstrating state-of-the-art performance on large datasets.
Contribution
It provides a geometric analysis and a provably correct active set method for elastic net regularization in subspace clustering, improving scalability and clustering quality.
Findings
Achieves state-of-the-art clustering accuracy.
Efficiently handles large-scale datasets.
Provides theoretical justification for elastic net balance.
Abstract
State-of-the-art subspace clustering methods are based on expressing each data point as a linear combination of other data points while regularizing the matrix of coefficients with , or nuclear norms. regularization is guaranteed to give a subspace-preserving affinity (i.e., there are no connections between points from different subspaces) under broad theoretical conditions, but the clusters may not be connected. and nuclear norm regularization often improve connectivity, but give a subspace-preserving affinity only for independent subspaces. Mixed , and nuclear norm regularizations offer a balance between the subspace-preserving and connectedness properties, but this comes at the cost of increased computational complexity. This paper studies the geometry of the elastic net regularizer (a mixture of the and norms) and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering· youtube
Taxonomy
TopicsFace and Expression Recognition · Remote-Sensing Image Classification · Advanced Clustering Algorithms Research
