Saved in:
Bibliographic Details
Main Authors: Malekian, Reihaneh, Ramdas, Aaditya
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.05998
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929457157111808
author Malekian, Reihaneh
Ramdas, Aaditya
author_facet Malekian, Reihaneh
Ramdas, Aaditya
contents The matrix Markov inequality by Ahlswede was stated using the Loewner anti-order between positive definite matrices. Wang use this to derive several other Chebyshev and Chernoff-type inequalities (Hoeffding, Bernstein, empirical Bernstein) in the Loewner anti-order, including self-normalized matrix martingale inequalities. These imply upper tail bounds on the maximum eigenvalue, such as those developed by Tropp and howard et al. The current paper develops analogs of all these inequalities in the Loewner order, rather than anti-order, by deriving a new matrix Markov inequality. These yield upper tail bounds on the minimum eigenvalue that are a factor of d tighter than the above bounds on the maximum eigenvalue.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05998
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Matrix Concentration: Order versus Anti-order
Malekian, Reihaneh
Ramdas, Aaditya
Probability
The matrix Markov inequality by Ahlswede was stated using the Loewner anti-order between positive definite matrices. Wang use this to derive several other Chebyshev and Chernoff-type inequalities (Hoeffding, Bernstein, empirical Bernstein) in the Loewner anti-order, including self-normalized matrix martingale inequalities. These imply upper tail bounds on the maximum eigenvalue, such as those developed by Tropp and howard et al. The current paper develops analogs of all these inequalities in the Loewner order, rather than anti-order, by deriving a new matrix Markov inequality. These yield upper tail bounds on the minimum eigenvalue that are a factor of d tighter than the above bounds on the maximum eigenvalue.
title Matrix Concentration: Order versus Anti-order
topic Probability
url https://arxiv.org/abs/2408.05998