SqueezeFit: Label-aware dimensionality reduction by semidefinite programming
Machine Learning
2018-12-10 v1 Machine Learning
Optimization and Control
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.
Cite
@article{arxiv.1812.02768,
title = {SqueezeFit: Label-aware dimensionality reduction by semidefinite programming},
author = {Culver McWhirter and Dustin G. Mixon and Soledad Villar},
journal= {arXiv preprint arXiv:1812.02768},
year = {2018}
}