Corpus ID: 11031098

Explicit Approximations of the Gaussian Kernel

@article{Cotter2011ExplicitAO,
  title={Explicit Approximations of the Gaussian Kernel},
  author={Andrew Cotter and Joseph Keshet and Nathan Srebro},
  journal={ArXiv},
  year={2011},
  volume={abs/1109.4603}
}
  • Andrew Cotter, Joseph Keshet, Nathan Srebro
  • Published 2011
  • Computer Science
  • ArXiv
  • We investigate training and using Gaussian kernel SVMs by approximating the kernel with an explicit finite- dimensional polynomial feature representation based on the Taylor expansion of the exponential. Although not as efficient as the recently-proposed random Fourier features [Rahimi and Recht, 2007] in terms of the number of features, we show how this polynomial representation can provide a better approximation in terms of the computational cost involved. This makes our "Taylor features… CONTINUE READING
    An approximation of the Gaussian RBF kernel for efficient classification with SVMs
    • 36
    • Highly Influenced
    Optimal Rates for Random Fourier Features
    • 70
    • PDF
    Generalization Properties of Learning with Random Features
    • 142
    • PDF
    Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels
    • 3
    • PDF
    Memory Efficient Kernel Approximation
    • 107
    • PDF
    Fast Prediction with SVM Models Containing RBF Kernels
    • 28
    • PDF
    No-Trick (Treat) Kernel Adaptive Filtering using Deterministic Features
    • 1
    • PDF
    Large-Scale Data-Dependent Kernel Approximation
    • 8
    • PDF
    Large-Scale Approximate Kernel Canonical Correlation Analysis
    • 25
    • PDF
    Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES
    Random Features for Large-Scale Kernel Machines
    • 2,075
    • PDF
    Efficient SVM Training Using Low-Rank Kernel Representations
    • 637
    • PDF
    Uniform approximation of functions with random bases
    • 131
    • PDF
    A dual coordinate descent method for large-scale linear SVM
    • 854
    • PDF
    Training and Testing Low-degree Polynomial Data Mappings via Linear SVM
    • 349
    • PDF
    Fast Kernel Classifiers with Online and Active Learning
    • 663
    • PDF
    Kernels as features: On kernels, margins, and low-dimensional mappings
    • 137
    • Highly Influential
    • PDF
    COFFIN: A Computational Framework for Linear SVMs
    • 81
    • PDF