Kernel Matching Pursuit

By Pascal Vincent, Yoshua Bengio. Machine-mediated learning, 2002

345 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics

View Paper: https://www.semanticscholar.org/paper/8fcb66d7318bede9ca594026cbdd0de8e4390aa8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

Citations in the corpus

Training Invariant Support Vector Machines using Selective Sampling (2005, background): “To address those limitations, there has been a lot of clever studies on solving quadratic optimization problems [7] [18], on online learning [4] [19] [11], on sparse solutions [39], and on active learning [9] [6].”
Ranking a Random Feature for Variable and Feature Selection (2003, methodology): “…learning context for RBF networks by Chen et al. (1991), for neural networks by Urbani et al. (1993), and for wavelet networks by Oussar (1998), Oussar and Dreyfus (2000); variants of the method were developed recently under the name of Matching Pursuit (see for instance Vincent and Bengio, 2001).”
The kernel recursive least-squares algorithm (2004, background): “[19]–[21], but see [22] for an exception), in which case, the algorithm is free to choose any one of the training samples at each step of the construction process.”
Building Support Vector Machines with Reduced Classifier Complexity (2006, methodology): “Particularly relevant to the work in this paper are the kernel matching pursuit (KMP) algorithm of Vincent and Bengio (2002) and the growing support vector classifier (GSVC) algorithm of Parrado-Hernández et al. (2003).”
Large Scale Machine Learning (2004, methodology): “, 1999), Projection Pursuit (Vincent and Bengio, 2002) and Independent Component Analysis (Bach and Jordan, 2002).”
Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior (2010, background): “This problem is inherently ill-posed as there are generally multiple high-resolution images that can be reduced to the same lowresolution image.”
Decentralized Online Learning With Kernels (2017, methodology): “We form Di,t+1 by selecting a subset of Mi,t+1 columns from D̃i,t+1 that best approximate f̃i,t+1 in terms of Hilbert norm error, which may be done by executing kernel orthogonal matching pursuit (KOMP) [30], [46] with error tolerance t to find a kernel dictionary matrix Di,t+1 based on the one whic”
Storage Fit Learning with Feature Evolvable Streams (2020, background): “The optimal β i in (19) can be efficiently found by matching pursuit (Vincent and Bengio 2002).”
Machine Learning Methods for Predicting Failures in Hard Drives: A Multiple-Instance Application (2005, background): “Other researchers have noticed this propertyf SVMs and have developed algorithms that create smaller sets of support vectors, such as the relevanc vector machine (Tipping, 2001), kernel matching pursuit (Vincent and Bengio, 2002) and Bayesi n neural networks (Liang, 2003).”
Hyperspectral image classification via kernel sparse representation (2011, methodology): “Therefore, if the data set is not linearly separable, kernel methods [33]–[36] can be applied to project the data into a nonlinear feature space in which the data becomes more separable.”
A general regression technique for learning transductions (2005, methodology): “This consists, as with Kernel Matching Pursuit (KMP) (Vincent & Bengio, 2000), of defining a subsetn m of kernel functions in an incremental fashion.”