Kernel Matrix Evaluation
نویسندگان
چکیده
We study the problem of evaluating the goodness of a kernel matrix for a classification task. As kernel matrix evaluation is usually used in other expensive procedures like feature and model selections, the goodness measure must be calculated efficiently. Most previous approaches are not efficient, except for Kernel Target Alignment (KTA) that can be calculated in O(n) time complexity. Although KTA is widely used, we show that it has some serious drawbacks. We propose an efficient surrogate measure to evaluate the goodness of a kernel matrix based on the data distributions of classes in the feature space. The measure not only overcomes the limitations of KTA, but also possesses other properties like invariance, efficiency and error bound guarantee. Comparative experiments show that the measure is a good indication of the goodness of a kernel matrix.
منابع مشابه
An infeasible interior-point method for the $P*$-matrix linear complementarity problem based on a trigonometric kernel function with full-Newton step
An infeasible interior-point algorithm for solving the$P_*$-matrix linear complementarity problem based on a kernelfunction with trigonometric barrier term is analyzed. Each (main)iteration of the algorithm consists of a feasibility step andseveral centrality steps, whose feasibility step is induced by atrigonometric kernel function. The complexity result coincides withthe best result for infea...
متن کاملUsing a Novel Concept of Potential Pixel Energy for Object Tracking
Abstract In this paper, we propose a new method for kernel based object tracking which tracks the complete non rigid object. Definition the union image blob and mapping it to a new representation which we named as potential pixels matrix are the main part of tracking algorithm. The union image blob is constructed by expanding the previous object region based on the histogram feature. The pote...
متن کاملStructured Block Basis Factorization for Scalable Kernel Matrix Evaluation
Kernel matrices are popular in machine learning and scientific computing, but they are limited by their quadratic complexity in both construction and storage. It is well-known that as one varies the kernel parameter, e.g., the width parameter in radial basis function kernels, the kernel matrix changes from a smooth low-rank kernel to a diagonally-dominant and then fully-diagonal kernel. Low-ran...
متن کاملA Geometry Preserving Kernel over Riemannian Manifolds
Abstract- Kernel trick and projection to tangent spaces are two choices for linearizing the data points lying on Riemannian manifolds. These approaches are used to provide the prerequisites for applying standard machine learning methods on Riemannian manifolds. Classical kernels implicitly project data to high dimensional feature space without considering the intrinsic geometry of data points. ...
متن کاملOptimization and performance evaluation of the IDR iterative Krylov solver on GPUs
In this paper, we present an optimized GPU implementation for the induced dimension reduction algorithm. We improve data locality, combine it with an efficient sparse matrix vector kernel, and investigate the potential of overlapping computation with communication as well as the possibility of concurrent kernel execution. A comprehensive performance evaluation is conducted using a suitable perf...
متن کامل