Corpus ID: 6161569

SPSD Matrix Approximation vis Column Selection: Theories, Algorithms, and Extensions

@article{Wang2016SPSDMA,
  title={SPSD Matrix Approximation vis Column Selection: Theories, Algorithms, and Extensions},
  author={Shusen Wang and Luo Luo and Z. Zhang},
  journal={J. Mach. Learn. Res.},
  year={2016},
  volume={17},
  pages={49:1-49:49}
}
  • Shusen Wang, Luo Luo, Z. Zhang
  • Published 2016
  • Computer Science, Mathematics
  • J. Mach. Learn. Res.
  • Symmetric positive semidefinite (SPSD) matrix approximation is an important problem with applications in kernel methods. However, existing SPSD matrix approximation methods such as the Nystrom method only have weak error bounds. In this paper we conduct in-depth studies of an SPSD matrix approximation model and establish strong relative-error bounds. We call it the prototype model for it has more efficient and effective extensions, and some of its extensions have high scalability. Though the… CONTINUE READING
    24 Citations
    Towards More Efficient SPSD Matrix Approximation and CUR Matrix Decomposition
    • 19
    • PDF
    Efficient large scale kernel ridge regression via ensemble SPSD approximation
    • 1
    • Highly Influenced
    Pass-Efficient Randomized Algorithms for Low-Rank Matrix Approximation Using Any Number of Views
    • 8
    • PDF
    Fast Generalized Matrix Regression with Applications in Machine Learning
    • PDF
    Robust Frequent Directions with Application in Online Learning
    • 8
    • PDF
    Scalable Gaussian Process Computations Using Hierarchical Matrices
    • 12
    • PDF
    Low-Rank PSD Approximation in Input-Sparsity Time
    • 22
    • PDF
    Sketchy Empirical Natural Gradient Methods for Deep Learning
    • 1
    • PDF
    Sublinear Time Low-Rank Approximation of Positive Semidefinite Matrices
    • Cameron Musco, D. Woodruff
    • Mathematics, Computer Science
    • 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS)
    • 2017
    • 27
    • PDF
    Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging
    • 45
    • PDF

    References

    SHOWING 1-10 OF 46 REFERENCES
    Towards More Efficient SPSD Matrix Approximation and CUR Matrix Decomposition
    • 19
    • PDF
    Improving CUR matrix decomposition and the Nyström approximation via adaptive sampling
    • 142
    • PDF
    Revisiting the Nystrom Method for Improved Large-scale Machine Learning
    • 282
    • Highly Influential
    • PDF
    Improved Bounds for the Nyström Method With Application to Kernel Classification
    • 45
    • PDF
    Memory Efficient Kernel Approximation
    • 110
    • Highly Influential
    • PDF
    Towards More Efficient Symmetric Matrix Sketching and the CUR Matrix Decomposition
    • 7
    Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions
    • 2,550
    • PDF
    The matrix ridge approximation: algorithms and applications
    • Z. Zhang
    • Mathematics, Computer Science
    • Machine Learning
    • 2013
    • 10
    • PDF
    Matrix approximation and projective clustering via volume sampling
    • 281
    • Highly Influential
    • PDF
    On the Nyström Method for Approximating a Gram Matrix for Improved Kernel-Based Learning
    • 840
    • PDF