7
$\begingroup$

I was learning about regularization and came across the term called regularization parameter.

I see that it is called lambda in theory but when I looked at the python implementation, I see that it is denoted as alpha. Here is the link1 and link2

Am I right to understand that both mean the same?

Is there any difference between regularization paramter lambda and regularization parameter alpha ?

$\endgroup$
22
$\begingroup$

No difference. It's just a symbol. Sometimes mathematics uses symbols by convention, but there's no rule or requirement that you must use a certain symbol for a concept.

In this particular case, the word lambda is reserved by the Python language, so alpha avoids overlapping with that word.

As an aside, one sharp corner in sklearn is that sklearn.linear_model.LogisticRegression uses the inverse of regularization strength as the regularization parameter, so $C=\lambda^{-1}$. In a different package, you might set $\lambda=10$, but for this class, you would get an equivalent result with $C=0.1$.

$\endgroup$
0

Your Answer

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

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