1
$\begingroup$

Let $X$ be a given $d \times T$ matrix, and let $M$ be an $n \times d$ random matrix (say i.i.d. centered coefficients). Define $Y=MX$ in $\mathbb{R}^n$ and $H=Y'(YY')^{-1}Y$, where $'$ denotes the transpose operator. We assume $n<T$. The question is: is it possible to estimate the scalar quantity $$E=\mathbb{E}[\|HX - X\|^2]$$ as a function of $n, T, d$ and probably some quantities related to $X$?

$\endgroup$

1 Answer 1

1
$\begingroup$

It depends on the matrix norm that you are referring inside the expectation.

There is a huge literature on the related problem of approximating solving Least Squares by random projections. Hope this helps.

Paper

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.