Fast SVM training using approximate extreme points

TL;DR

This paper introduces AESVM, a fast approximation method for training non-linear kernel SVMs on large datasets, achieving significant speedups while maintaining comparable accuracy.

Contribution

AESVM uses a representative subset of data to significantly reduce training time for kernel SVMs, with analytical guarantees of solution similarity.

Findings

AESVM trains up to 1000 times faster than LIBSVM on large datasets.

AESVM maintains similar classification accuracy to LIBSVM across multiple datasets.

AESVM offers faster classification times compared to traditional SVM methods.

Abstract

Applications of non-linear kernel Support Vector Machines (SVMs) to large datasets is seriously hampered by its excessive training time. We propose a modification, called the approximate extreme points support vector machine (AESVM), that is aimed at overcoming this burden. Our approach relies on conducting the SVM optimization over a carefully selected subset, called the representative set, of the training dataset. We present analytical results that indicate the similarity of AESVM and SVM solutions. A linear time algorithm based on convex hulls and extreme points is used to compute the representative set in kernel space. Extensive computational experiments on nine datasets compared AESVM to LIBSVM \citep{LIBSVM}, CVM \citep{Tsang05}, BVM \citep{Tsang07}, LASVM \citep{Bordes05}, $\text{SVM}^{\text{perf}}$ \citep{Joachims09}, and the random features method \citep{rahimi07}. Our AESVM implementation was found to train much faster than the other methods, while its classification accuracy was similar to that of LIBSVM in all cases. In particular, for a seizure detection dataset, AESVM training was almost $10^3$ times faster than LIBSVM and LASVM and more than forty times faster than CVM and BVM. Additionally, AESVM also gave competitively fast classification times.