A Refined Non-Asymptotic Tail Bound of Sub-Gaussian Matrix
Received:June 25, 2019  Revised:May 02, 2020
Key Word: non-asymptotic theory   largest singular value   tail bound   sub-Gaussian matrix  
Fund ProjectL:Supported by the Fundamental Research Funds for the Central Universities (Grant No.DUT20LK38).
Author NameAffiliation
Xianjie GAO School of Mathematical Sciences, Dalian University of Technology, Liaoning 116024, P. R. China 
Chao ZHANG School of Mathematical Sciences, Dalian University of Technology, Liaoning 116024, P. R. China 
Hongwei ZHANG School of Mathematical Sciences, Dalian University of Technology, Liaoning 116024, P. R. China 
Hits: 27
Download times: 0
Abstract:
      In this paper, we obtain a refined non-asymptotic tail bound for the largest singular value (the soft edge) of sub-Gaussian matrix. As an application, we use the obtained theorem to compute the tail bound of the Gaussian Toeplitz matrix.
Citation:
DOI:10.3770/j.issn:2095-2651.2020.05.010
View Full Text  View/Add Comment  Download reader