A PARTAN-Accelerated Frank-Wolfe Algorithm for Large-Scale SVM Classification

TL;DR

This paper introduces a PARTAN-accelerated Frank-Wolfe algorithm tailored for large-scale SVM classification, demonstrating improved efficiency and performance on benchmark datasets through experiments.

Contribution

It presents the novel application of the PARTAN variant of Frank-Wolfe to large-scale SVMs, enhancing existing algorithms with new theoretical and practical insights.

Findings

Promising results on medium and large-scale datasets

Improved convergence and efficiency over standard methods

Effective use of stochastic speed-up techniques

Abstract

Frank-Wolfe algorithms have recently regained the attention of the Machine Learning community. Their solid theoretical properties and sparsity guarantees make them a suitable choice for a wide range of problems in this field. In addition, several variants of the basic procedure exist that improve its theoretical properties and practical performance. In this paper, we investigate the application of some of these techniques to Machine Learning, focusing in particular on a Parallel Tangent (PARTAN) variant of the FW algorithm that has not been previously suggested or studied for this type of problems. We provide experiments both in a standard setting and using a stochastic speed-up technique, showing that the considered algorithms obtain promising results on several medium and large-scale benchmark datasets for SVM classification.