NIPS Poster But How Does It Work in Theory? Linear SVM with Random Features

Poster

But How Does It Work in Theory? Linear SVM with Random Features

Yitong Sun · Anna Gilbert · Ambuj Tewari

Room 517 AB #128

Keywords: [ Kernel Methods ] [ Learning Theory ] [ Regularization ] [ Spaces of Functions and Kernels ]

[ Abstract ]

Abstract: We prove that, under low noise assumptions, the support vector machine with $N\ll m$ random features (RFSVM) can achieve the learning rate faster than $O(1/\sqrt{m})$ on a training set with $m$ samples when an optimized feature map is used. Our work extends the previous fast rate analysis of random features method from least square loss to 0-1 loss. We also show that the reweighted feature selection method, which approximates the optimized feature map, helps improve the performance of RFSVM in experiments on a synthetic data set.

Live content is unavailable. Log in and register to view live content