… Matching Pursuit algorithms learn a function that is a weighted sum of … matching pursuit
can be extended to use non-squared error loss functions, and how it can be used to build kernel-…

… Kernel matching pursuit is a greedy algorithm for building an approximation of a … a
kernel-induced dictionary. Here we propose a modification of the kernel matching pursuit algorithm …

… We analyse matching pursuit for kernel principal components … matching pursuit algorithm
called kernel matching pursuit (… can be applied to other matching pursuit related algorithms. …

… We take the idea of Matching Pursuit, due to its very fast greedy iterative nature, and apply
it to Kernel Fisher Discriminant Analysis in order to impose dual sparsity. We prove that this …

… kernel-based method, which exploits greedy selection techniques, particularly Orthogonal
Matching Pursuit (… function via the mapping to a Reproducing Kernel Hilbert Space (RKHS). …

… Note that MKL-GOMP should not be confused with Kernel Matching Pursuit [28] whose goal
is different: it is designed to sparsify α in a single-kernel setting. The MKL-GOMP procedure …

… Matching Pursuit and the Basis Pursuit. We will explain the building and the use of the multiple
kernels, combined with the LARS in section 3. Section 4 deals with the setting of the bias-…

… In the kernel matching pursuit analysis we will convert the regression loss of KMP into a
classification loss in order to apply the above results. In the regression analysis of sparse …

… Kernel Matching Pursuit (KMP) is simply the idea of applying the Matching Pursuit (MP)
family of algorithms to problem in machine learning, using a kernel-based dictionary [1]. Given a …

… 2 Basic Matching Pursuit and Kernel Matching Pursuit In the following, basic matching
pursuit and kernel matching pursuit are addressed. The former was first proposed by Mallat and …