Efficient Kernel Machines Using the Improved Fast Gauss Transform
نویسندگان
چکیده
The computation and memory required for kernel machines with N training samples is at least O(N). Such a complexity is significant even for moderate size problems and is prohibitive for large datasets. We present an approximation technique based on the improved fast Gauss transform to reduce the computation to O(N). We also give an error bound for the approximation, and provide experimental results on the UCI datasets.
منابع مشابه
Improved fast Gauss transform User manual
In most kernel based machine learning algorithms and non-parametric statistics the key computational task is to compute a linear combination of local kernel functions centered on the training data, i.e., f(x) = ∑N i=1 qik(x, xi), which is the discrete Gauss transform for the Gaussian kernel. f is the regression/classification function in case of regularized least squares, Gaussian process regre...
متن کاملImproved Fast Gauss Transform and Efficient Kernel Density Estimation
Evaluating sums of multivariate Gaussians is a common computational task in computer vision and pattern recognition, including in the general and powerful kernel density estimation technique. The quadratic computational complexity of the summation is a significant barrier to the scalability of this algorithm to practical applications. The fast Gauss transform (FGT) has successfully accelerated ...
متن کاملInsights on Fast Kernel Density Estimation Algorithms
We present results of experiments testing the Fast Gauss Transform, Improved Fast Gauss Transform, and Dual-Tree methods (using kd-tree and Anchors Hierarchy data structures) for fast Kernel Density Estimation (KDE). We examine the performance of these methods with respect to data set size, dimension, allowable error, and data set structure (“clumpiness”), measured in terms of CPU time and memo...
متن کاملEmpirical Testing of Fast Kernel Density Estimation Algorithms
We present results of experiments testing the Fast Gauss Transform, Improved Fast Gauss Transform, and Dual-Tree methods (using kd-tree and Anchors Hierarchy data structures) for fast Kernel Density Estimation (KDE). We examine the performance of these methods with respect to data set size, dimension, allowable error, and data set structure (“clumpiness”), measured in terms of CPU time and memo...
متن کاملPROPOSAL : EFFICIENT KERNEL DENSITY ESTIMATION AND ROBUST REAL - TIME OBJECT TRACKING by
Evaluating sums of multivariate Gaussians is a common computational task in computer vision and pattern recognition, including in the general and powerful kernel density estimation technique. The quadratic computational complexity of the summation is a significant barrier to the scalability of this algorithm to practical applications. The fast Gauss transform (FGT) has successfully accelerated ...
متن کامل