Matrix Concentration for Products
Abstract
This paper develops nonasymptotic growth and concentration bounds for a product of independent random matrices. These results sharpen and generalize recent work of Henriksen–Ward, and they are similar in spirit to the results of Ahlswede–Winter and of Tropp for a sum of independent random matrices. The argument relies on the uniform smoothness properties of the Schatten trace classes.
Additional Information
© SFoCM 2021. Received 04 April 2020; Revised 04 March 2021; Accepted 17 June 2021; Published 13 August 2021. The authors gratefully acknowledge the funding for this work. DH was supported under NSF Grant DMS-1613861. JNW and RW were supported in part by the Institute for Advanced Study, where some of this research was conducted. JAT was supported under ONR Awards N00014-17-1-2146 and N00014-18-1-2363. RW also received support from AFOSR MURI Award N00014-17-S-F006. Communicated by Alan Edelman.
Attached Files
Submitted - 2003.05437.pdf
Files
Name | Size | Download all |
---|---|---|
md5:084d59f2f64f6ab7f567530af0fba44f
|
319.5 kB | Preview Download |
Additional details
- Eprint ID
- 107219
- Resolver ID
- CaltechAUTHORS:20201218-154434116
- DMS-1613861
- NSF
- Institute for Advanced Study
- N00014-17-1-2146
- Office of Naval Research (ONR)
- N00014-18-1-2363
- Office of Naval Research (ONR)
- N00014-17-S-F006
- Air Force Office of Scientific Research (AFOSR)
- Created
-
2020-12-21Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field