Fast Training of Support Vector Machines using Sequential Minimal Optimization

By J. Platt. 2000

How researchers see this paper

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

In Optimization & Training

Citations in the corpus

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “In contrast to binary SVM, regularization paths for multiclass SVMs are more complex and less studied.”
Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers (2013, methodology): “In particular, we considered an SVM classiﬁer based on the SMO module (Sequential Minimal Optimization [50]) of the Weka framework.”
Stochastic dual coordinate ascent methods for regularized loss (2012, neutral): “DCA methods are related to decomposition methods [12, 5].”
Coordinate descent algorithms (2015, methodology): “In the best known early application of coordinate descent to SVM, Platt [42] deals with a hinge-loss formulation of SVM, which is identical to (18) except that the square on each term of the summation is omitted.”
Kernel methods in machine learning (2007, neutral): “[132] a similar selection criterion is utilized with respect to margin violations, leading to an SMO-like optimization algorithm (Platt [107]).”
Learn to Solve Algebra Word Problems Using Quadratic Programming (2015, methodology): “This is a QP problem and has been well studied (Platt, 1999; Fan et al., 2008).”
A Parallel Mixture of SVMs for Very Large Scale Problems (2001, background): “Note however that current state-of-the-art algorithms appear to have training time complexity scaling much closer to O(N(2)) than O(N(3)) (Collobert & Bengio, 2001; Joachims, 1999; Platt, 1999).”
How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets (2014, methodology): “An early version of this idea was reflected in the Sequential Minimal Optimization (SMO) algorithm [37].”
Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors (2007, methodology): “Sequential minimal optimization (SMO) proposed by Platt (1999) is a simple algorithm that can be used to solve the SVM-QP problem.”
A novel Frank-Wolfe algorithm. Analysis and applications to large-scale SVM training (2013, methodology): “1 Experiments on the Web Dataset Collection The Web Dataset Collection is a series of classification problems extracted from a webpage categorization dataset, first appeared in Platt’s paper on Sequential Minimal Optimization for training SVMs [45].”
A Convex Feature Learning Formulation for Latent Task Structure Discovery (2012, methodology): “Hence we use a sequential minimal optimization (SMO) algorithm (Platt, 1999) for solving (5).”
Learning to Rank Using User Clicks and Visual Features for Image Retrieval (2015, methodology): “This is a standard quadratic programming problem which can be solved by using efficient algorithms such as the interior point method [26], or sequential minimal optimization [27] if the constraint number is huge.”
Text mining for market prediction: A systematic review (2014, methodology): “Schumaker et al. (2012) choose to implement the SVR Sequential Minimal Optimization (Platt, 1999) function through Weka (Witten & Frank, 2005).”