Cupitor

# 168 Actions

 2018 2017 Jul 9 awarded Notable Question Aug 24 comment Does Regularized Logistic Regression Produce Calibrated Results? Could you please write your answer as a solution so I could accept it? thank you! Aug 24 comment Does Regularized Logistic Regression Produce Calibrated Results? @FrankHarrell thank you for a completed answer, but I think Alex is right here, check his comments under my question. But thanks a lot for the explanation. Aug 24 comment Does Regularized Logistic Regression Produce Calibrated Results? @RossGayler I think Alex's answer was more helpful. It seems it does not depend on the regularization; if you do not penalize the intercept (which is common) it still remains calibrated. Aug 24 comment Does Regularized Logistic Regression Produce Calibrated Results? Oh I am totally sorry. I get it now. Fair enough! That solves the issue :) Aug 24 comment Does Regularized Logistic Regression Produce Calibrated Results? @Alex, thanks for your input. Cardinl's reasoning in my humble opinion does not follows since after taking derivates there will be an extra term of $+\lambda \beta_i$ in the equations instead of zero on the other side. In other words the regularization factor of. $\lambda \|\beta\|^2$ will not cancel when taking derivatives. Aug 21 comment Does Regularized Logistic Regression Produce Calibrated Results? @RossGayler thank you for sharing the sentiment. I was confused. I can see that the proof does not follow so it is not surprising. But it is surprising that there is nothing written about it out there. Aug 20 comment Does Regularized Logistic Regression Produce Calibrated Results? Thank you. But I am not sure if I understand the connection of your answer to calibration. No matter how the regularization coefficient is chosen eventually we end up with a learned model based on optimization. The question is whether that model is calibrated meaning that $\hat{p}(y=1)\approx p(y=1)$. Aug 20 asked Does Regularized Logistic Regression Produce Calibrated Results? May 30 awarded Nice Question May 29 awarded Popular Question Apr 19 awarded Yearling Mar 19 awarded Famous Question Feb 5 comment Expectation of Multidimensional Function of Random Variables w.r.t. Marginal Distribution Thank you for your reply. I am very confused. What I am wondering is that either $\int f(X,Y)dP(y)$ is well-defined or not. And if not, why not? I guess I am having a conversation on math.stackexchange but thanks a lot. Feb 4 revised Expectation of Multidimensional Function of Random Variables w.r.t. Marginal Distribution added 44 characters in body Feb 4 asked Expectation of Multidimensional Function of Random Variables w.r.t. Marginal Distribution Apr 30 awarded Nice Question Apr 3 comment Kullback-Leibler Divergence just wanted to remind that you never came back :P Feb 16 awarded Notable Question Feb 15 awarded Popular Question