A sequential dual method for large scale multi-class linear svms

Abstract

Efficient training of direct multi-class formulations of linear Support Vector Machines is very useful in applications such as text classification with a huge number examples as well as features. This paper presents a fast dual method for this training. The main idea is to sequentially traverse through the training set and optimize the dual variables associated with one example at a time. The speed of training is enhanced further by shrinking and cooling heuristics. Experiments indicate that our method is much faster than state of the art solvers such as bundle, cutting plane and exponentiated gradient methods.

Keywords

TraverseHeuristicsSupport vector machineDual (grammatical number)Computer scienceClass (philosophy)Set (abstract data type)Training setSpeedupAlgorithmArtificial intelligencePattern recognition (psychology)Mathematical optimizationMathematicsParallel computing

Affiliated Institutions

Related Publications

Fast Training of Support Vector Machines Using Sequential Minimal Optimization

John Platt

This chapter describes a new algorithm for training Support Vector Machines: Sequential Minimal Optimization, or SMO. Training a Support Vector Machine (SVM) requires the soluti...

1998 The MIT Press eBooks 5457 citations

A Discriminative Framework for Modelling Object Classes

Alex Holub , Pietro Perona

Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn...

2005 56 citations

Kernel Logistic Regression and the Import Vector Machine

Ji Zhu , Trevor Hastie

The support vector machine (SVM) is known for its good performance in two-class classification, but its extension to multiclass classification is still an ongoing research issue...

2001 136 citations

Part-Based Statistical Models for Object Classification and Detection

Elliot Joel Bernstein , Yali Amit

We propose using simple mixture models to define a set of mid-level binary local features based on binary oriented edge input. The features capture natural local structures in t...

2005 31 citations

Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

Tara N. Sainath , Bhuvana Ramabhadran , Michael Picheny +2 more

The use of exemplar-based methods, such as support vector machines (SVMs), k-nearest neighbors (kNNs) and sparse representations (SRs), in speech recognition has thus far been l...

2011 IEEE Transactions on Audio Speech and... 65 citations

Publication Info

Year: 2008
Type: article
Pages: 408-416
Citations: 152
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

A sequential dual method for large scale multi-class linear svms

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

152

OpenAlex

Cite This

APA Style

                            
                                    S. Sathiya Keerthi, 
                                
                                    S. Sundararajan, 
                                
                                    Kai‐Wei Chang
                                
                                et al.
                            
                            (2008). 
                            A sequential dual method for large scale multi-class linear svms. 
                            
                            , 408-416.
                            https://doi.org/10.1145/1401890.1401942

Identifiers

DOI: 10.1145/1401890.1401942