A fast iterative nearest point algorithm for support vector machine classifier design

By S. Sathiya Keerthi, Shirish K. Shevade, C. Bhattacharyya, K. Murthy. IEEE Trans. Neural Networks Learn. Syst., 2000

419 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Networks and Communications, Numerical Analysis

View Paper: https://www.semanticscholar.org/paper/5420f5910b6a32c0ebed26b1f3b61ad6f7d75277

How researchers see this paper

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

In Computational Mechanics

In Computer Networks and Communications

In Numerical Analysis

Citations in the corpus

Anomaly Detection in Vertically Partitioned Data by Distributed Core Vector Machines (2013, methodology): “The algorithm uses a modiﬁed kernel function ˜ k for the reason that optimization problem (1) yields a hard margin solution, but can be transformed into a soft margin problem [19] The new kernel again satisﬁes ˜ k ( z , z ) = ˜ κ with ˜ κ being constant.”
QP Algorithms with Guaranteed Accuracy and Run Time for Support Vector Machines (2006, methodology): “Lin (2001a) performs a convergence rate analysis that may eventually be used to establish run time bounds for a popular decomposition algorithm, but these results hold under rather restrictive assumptions and more work is needed before the tightness and utility of these bounds is known (a more recen”
Core Vector Machines: Fast SVM Training on Very Large Data Sets (2005, background): “Moreover, we followed http://www.csie.ntu.edu.tw/∼cjlin/libsvm/faq.html in adapting the LIBSVM package for L2-SVM.”
A novel Frank-Wolfe algorithm. Analysis and applications to large-scale SVM training (2013, methodology): “(1) This problem encompasses several models used in machine learning [13, 28], including hard-margin Support Vector Machines (SVMs) [36] and L2-loss SVMs (L2-SVMs) for binary classification, regression and novelty detection [58, 59].”
Introduction to Support Vector Machines (2002, methodology): “See (Keerthi, et al. 1999a) for a method of training SMV's in such a geometric way.”
An Equivalence between the Lasso and Support Vector Machines (2013, background): “, [26, 43].”
Support Vector Machine Solvers (2007, background): “There are also alternate formulations of the dual problem (Keerthi et al., 1999; Bennett and Bredensteiner, 2000).”
Coresets for polytope distance (2009, methodology): “By keeping the lengths of all projections onto the previous estimate in memory, one can in each step update the all projections by just calculating n scalar products (of the new point pi to all points in P ) [16], therefore the number of kernel evaluations (scalar product computations) is n in each ”
Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms (2002, methodology): “Since the constraints in (6) do not depend on the hyperparameters, can be directly carried over for the solution of (6) at . For (4), we already said that the nearest point formulation in [ 5 ] is employed.”
Duality and Geometry in SVM Classifiers (2000, background): “From an optimization perspective the reduced-convex-hull formulations may be preferable due to the interpretability of the misclassification parameter and the availability of fast nearest point in polytope algorithms (Keerthi et al., 1999).”