The doc (v1.10.0) says the gradient of the function
eigvalsh is always numerically stable – I’m wondering why it’s the case?
eigvalsh internally invokes
eigh of which the backward pass is problematic when there’re repeated eigenvalues. So why the problem just goes away when we only want the derivatives of eigenvalues?
In other words, why only differentiating eigenvalues is ok, both theory-wise and implementation-wise?
Can someone enlighten me?