Abstract | ||
---|---|---|
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" especially attractive for use on very large data sets, in conjunction with online or stochastic training. |
Year | Venue | Keywords |
---|---|---|
2011 | CoRR | gaussian kernel,artificial intelligent,taylor expansion |
Field | DocType | Volume |
Kernel (linear algebra),Polynomial,Computer science,Kernel embedding of distributions,Kernel principal component analysis,Polynomial kernel,Artificial intelligence,Gaussian function,Variable kernel density estimation,Machine learning,Taylor series | Journal | abs/1109.4603 |
Citations | PageRank | References |
9 | 0.51 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andrew Cotter | 1 | 851 | 78.35 |
Joseph Keshet | 2 | 925 | 69.84 |
Nathan Srebro | 3 | 3892 | 349.42 |