Here's one thing i noticed. In Elementary Real Analysis, when we say that a sequence $s_n$ converges to a point $s$, we first set an $\epsilon > 0$ such that for large $N \in \mathbb{N} $ $| s_n - s | < \epsilon. $

Why don't we set up the convergence of loss functions that way? i. e. We don't have a hyperparameterhyperparameter $\epsilon$ to ensure our convergence.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.