Beta. Content is under active construction and has not been peer-reviewed. Report errors on
GitHub
.
Disclaimer
Theorem
Path
Curriculum
Paths
Demos
Diagnostic
Search
Quiz Hub
/
Matrix Concentration
Matrix Concentration
1 questions
Difficulty 7-7
View topic
Advanced
0 / 1
1 advanced
Adapts to your performance
1 / 1
advanced (7/10)
conceptual
In the matrix Bernstein inequality, you bound the spectral norm of a sum of independent centered random matrices. Which quantity replaces the scalar variance in the bound?
Hide and think first
A.
The Frobenius norm of the sum of covariance matrices:
∥
∑
Cov
(
vec
(
A
i
))
∥
F
B.
The matrix variance statistic
σ
2
=
max
{
∥
∑
E
[
A
i
A
i
T
]
∥
,
∥
∑
E
[
A
i
T
A
i
]
∥
}
C.
The maximum eigenvalue of each individual
A
i
D.
The trace of
∑
E
[
A
i
2
]
Submit Answer