Bernstein Concentration Inequalities for Tensors via Einstein Products

Ziyan Luo, Liqun Qi, Philippe Toint

Research output: Working paper

Abstract

A generalization of the Bernstein matrix concentration inequality to random tensors of general order is proposed. This generalization is based on the use of
Einstein products between tensors, from which a strong link can be established
between matrices and tensors, in turn allowing exploitation of existing
results for the former.
LanguageEnglish
PublisherArxiv
Number of pages12
Volume1902.03056
Publication statusPublished - 11 Feb 2019

Fingerprint

Bernstein Inequality
Concentration Inequalities
Albert Einstein
Tensors
Tensor
Exploitation
Matrix Inequality
Generalization

Keywords

  • Random linear algebra
  • subsampling methods
  • computational statistics
  • concentration inequality
  • Einstein products

Cite this

@techreport{292d79ea18c74dce9fcb55ae87928eb9,
title = "Bernstein Concentration Inequalities for Tensors via Einstein Products",
abstract = "A generalization of the Bernstein matrix concentration inequality to random tensors of general order is proposed. This generalization is based on the use ofEinstein products between tensors, from which a strong link can be establishedbetween matrices and tensors, in turn allowing exploitation of existingresults for the former.",
keywords = "Random linear algebra, subsampling methods, computational statistics, concentration inequality, Einstein products",
author = "Ziyan Luo and Liqun Qi and Philippe Toint",
year = "2019",
month = "2",
day = "11",
language = "English",
volume = "1902.03056",
publisher = "Arxiv",
type = "WorkingPaper",
institution = "Arxiv",

}

Bernstein Concentration Inequalities for Tensors via Einstein Products. / Luo, Ziyan; Qi, Liqun; Toint, Philippe.

Arxiv, 2019.

Research output: Working paper

TY - UNPB

T1 - Bernstein Concentration Inequalities for Tensors via Einstein Products

AU - Luo, Ziyan

AU - Qi, Liqun

AU - Toint, Philippe

PY - 2019/2/11

Y1 - 2019/2/11

N2 - A generalization of the Bernstein matrix concentration inequality to random tensors of general order is proposed. This generalization is based on the use ofEinstein products between tensors, from which a strong link can be establishedbetween matrices and tensors, in turn allowing exploitation of existingresults for the former.

AB - A generalization of the Bernstein matrix concentration inequality to random tensors of general order is proposed. This generalization is based on the use ofEinstein products between tensors, from which a strong link can be establishedbetween matrices and tensors, in turn allowing exploitation of existingresults for the former.

KW - Random linear algebra

KW - subsampling methods

KW - computational statistics

KW - concentration inequality

KW - Einstein products

M3 - Working paper

VL - 1902.03056

BT - Bernstein Concentration Inequalities for Tensors via Einstein Products

PB - Arxiv

ER -