Upper bound for smallest eigenvalue of matrix ‖ ϕ ( x ) ‖ 2 ≤...
Upper bound for smallest eigenvalue of matrix
I am reading a paper which claims the following. But I am not sure how to show it rigorously. Any help is appreciated.
For all , assume the d-dimensional feature map is bounded such that . For any data distribution consider the matrix
Prove that the largest possible minimum eigenvalue min of matrix A satisfies