NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings

Volume: 63, Issue: 22, Pages: 6109 - 6121
Published: Jul 1, 2015
Abstract
We propose a novel framework for the deterministic construction of linear, near-isometric embeddings of a finite set of data points. Given a set of training points null null {\cal X} \subset {\BBR}^Nnull , we consider the secant set null null {\cal S}({\cal X})null null that consists of all pairwise difference vectors of null null {\cal X}null , normalized to lie on the unit sphere. We formulate an affine rank minimization problem to...
Paper Details
Title
NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings
DOI
Published Date
Jul 1, 2015
Journal
Volume
63
Issue
22
Pages
6109 - 6121
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.