Learning Data Manifolds with a Cutting Plane Method

doi:10.1162/neco_a_01119

Learning Data Manifolds with a Cutting Plane Method

2018-10-01

0

OA

AI

DOI：10.1162/neco_a_01119

原文链接

查看原文

摘要

En 中文

We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely on sampling large numbers of training examples from these manifolds. Instead, we propose an iterative algorithm, [Formula: see text], based on a cutting plane approach that efficiently solves a quadratic semi-infinite programming problem to find the maximum margin solution. We provide a proof of convergence as well as a polynomial bound on the number of iterations required for a desired tolerance in the objective function. The efficiency and performance of [Formula: see text] are demonstrated in high-dimensional simulations and on image manifolds generated from the ImageNet data set. Our results indicate that [Formula: see text] is able to rapidly learn good classifiers and shows superior generalization performance compared with conventional maximum margin methods using data augmentation methods.

Learning Data Manifolds with a Cutting Plane Method

摘要

AI总结

期刊

机构

引用论文