Matrix Concentration for Products
Autor: | Joel A. Tropp, Jonathan Niles-Weed, Rachel Ward, De Huang |
---|---|
Rok vydání: | 2021 |
Předmět: |
Pure mathematics
Work (thermodynamics) Trace (linear algebra) Smoothness (probability theory) Applied Mathematics Numerical analysis Probability (math.PR) Computational Mathematics Matrix (mathematics) Computational Theory and Mathematics Product (mathematics) FOS: Mathematics Random matrix Mathematics - Probability Analysis Mathematics |
Zdroj: | Foundations of Computational Mathematics. 22:1767-1799 |
ISSN: | 1615-3383 1615-3375 |
Popis: | 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. Comment: 21 pages |
Databáze: | OpenAIRE |
Externí odkaz: |