End-to-end Kernel Learning via Generative Random Fourier Features

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Kun, Liu, Fanghui, Huang, Xiaolin, Yang, Jie
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909072327966720
author Fang, Kun
Liu, Fanghui
Huang, Xiaolin
Yang, Jie
author_facet Fang, Kun
Liu, Fanghui
Huang, Xiaolin
Yang, Jie
contents Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learning the optimal feature map is often formulated as a target alignment problem, which aims to align the learned kernel with the pre-defined target kernel (usually the ideal kernel). In the second-stage process, a linear learner is conducted with respect to the mapped random features. Nevertheless, the pre-defined kernel in target alignment is not necessarily optimal for the generalization of the linear learner. Instead, in this paper, we consider a one-stage process that incorporates the kernel learning and linear learner into a unifying framework. To be specific, a generative network via RFFs is devised to implicitly learn the kernel, followed by a linear classifier parameterized as a full-connected layer. Then the generative network and the classifier are jointly trained by solving the empirical risk minimization (ERM) problem to reach a one-stage solution. This end-to-end scheme naturally allows deeper features, in correspondence to a multi-layer structure, and shows superior generalization performance over the classical two-stage, RFFs-based methods in real-world classification tasks. Moreover, inspired by the randomized resampling mechanism of the proposed method, its enhanced adversarial robustness is investigated and experimentally verified.
format Preprint
id arxiv_https___arxiv_org_abs_2009_04614
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle End-to-end Kernel Learning via Generative Random Fourier Features
Fang, Kun
Liu, Fanghui
Huang, Xiaolin
Yang, Jie
Machine Learning
Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. Current RFFs-based kernel learning methods usually work in a two-stage way. In the first-stage process, learning the optimal feature map is often formulated as a target alignment problem, which aims to align the learned kernel with the pre-defined target kernel (usually the ideal kernel). In the second-stage process, a linear learner is conducted with respect to the mapped random features. Nevertheless, the pre-defined kernel in target alignment is not necessarily optimal for the generalization of the linear learner. Instead, in this paper, we consider a one-stage process that incorporates the kernel learning and linear learner into a unifying framework. To be specific, a generative network via RFFs is devised to implicitly learn the kernel, followed by a linear classifier parameterized as a full-connected layer. Then the generative network and the classifier are jointly trained by solving the empirical risk minimization (ERM) problem to reach a one-stage solution. This end-to-end scheme naturally allows deeper features, in correspondence to a multi-layer structure, and shows superior generalization performance over the classical two-stage, RFFs-based methods in real-world classification tasks. Moreover, inspired by the randomized resampling mechanism of the proposed method, its enhanced adversarial robustness is investigated and experimentally verified.
title End-to-end Kernel Learning via Generative Random Fourier Features
topic Machine Learning
url https://arxiv.org/abs/2009.04614