학술논문
SqueezeFit: Label-Aware Dimensionality Reduction by Semidefinite Programming
Document Type
Periodical
Author
Source
IEEE Transactions on Information Theory IEEE Trans. Inform. Theory Information Theory, IEEE Transactions on. 66(6):3878-3892 Jun, 2020
Subject
Language
ISSN
0018-9448
1557-9654
1557-9654
Abstract
Given labeled points in a high-dimensional vector space, we seek a low-dimensional subspace such that projecting onto this subspace maintains some prescribed distance between points of differing labels. Intended applications include compressive classification. Taking inspiration from large margin nearest neighbor classification, this paper introduces a semidefinite relaxation of this problem. Unlike its predecessors, this relaxation is amenable to theoretical analysis, allowing us to provably recover a planted projection operator from the data.