首页    期刊浏览 2024年09月14日 星期六
登录注册

文章基本信息

  • 标题:The Johnson-Lindenstrauss Lemma Is Optimal for Linear Dimensionality Reduction
  • 本地全文:下载
  • 作者:Kasper Green Larsen ; Jelani Nelson
  • 期刊名称:LIPIcs : Leibniz International Proceedings in Informatics
  • 电子版ISSN:1868-8969
  • 出版年度:2016
  • 卷号:55
  • 页码:82:1-82:11
  • DOI:10.4230/LIPIcs.ICALP.2016.82
  • 出版社:Schloss Dagstuhl -- Leibniz-Zentrum fuer Informatik
  • 摘要:For any n > 1, 0 n^C for some constant C > 0, we show the existence of an N-point subset X of l_2^n such that any linear map from X to l_2^m with distortion at most 1 + epsilon must have m = Omega(min{n, epsilon^{-2}*lg(N)). This improves a lower bound of Alon [Alon, Discre. Mathem., 1999], in the linear setting, by a lg(1/epsilon) factor. Our lower bound matches the upper bounds provided by the identity matrix and the Johnson-Lindenstrauss lemma [Johnson and Lindenstrauss, Contem. Mathem., 1984].
  • 关键词:dimensionality reduction; lower bounds; Johnson-Lindenstrauss
国家哲学社会科学文献中心版权所有