Robust Subspace Clustering via Tighter Rank Approximation
arXiv:1510.08971 · doi:10.1145/2806416.2806506
Abstract
Matrix rank minimization problem is in general NP-hard. The nuclear norm is used to substitute the rank function in many recent studies. Nevertheless, the nuclear norm approximation adds all singular values together and the approximation error may depend heavily on the magnitudes of singular values. This might restrict its capability in dealing with many practical problems. In this paper, an arctangent function is used as a tighter approximation to the rank function. We use it on the challenging subspace clustering problem. For this nonconvex minimization problem, we develop an effective optimization procedure based on a type of augmented Lagrange multipliers (ALM) method. Extensive experiments on face clustering and motion segmentation show that the proposed method is effective for rank approximation.
arXiv commentACM CIKM 2015
References in corpus (10)
- Robust Recovery of Subspace Structures by Low-Rank Representation
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Proceedings of the 29th International Conference on Machine Learning (ICML-12)
- Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation
- A geometric analysis of subspace clustering with outliers
- Generalized Nonconvex Nonsmooth Low-Rank Minimization
- Multi-Stage Multi-Task Feature Learning
- Exact Subspace Segmentation and Outlier Detection by Low-Rank Representation
- Efficient Sparse Group Feature Selection via Nonconvex Optimization
- Noisy Sparse Subspace Clustering