Sir said its about differentiability…i understood it but sir also said it hace nice probabilistic interpretation – i didn’t understand this?
Why is mean squared error better than absolute error?
Hey @nikhil_sarda, could you please tell which video he said this, and at what time stamp, i need to check the reference in which he said so to answer correctly.
In the webinar of linear regression which was linked to YouTube.(1:10:35 first video of Machine Learning Introduction Topic) @S18CRX0120
Hey @nikhil_sarda, actually its related to task of penalizing those values, which are much far away, from the correct value, this means, that if actual value is, say 5, and one model predicted say 7 and other say predicted 50. So instead of saying that error is 2 for one, and 45 for 2, we also attempt to say that model 2 is even worse than that, because its value is much much far away. So we say, model 1 has error of 4 while model 2 has error of ( 2025 ). That is the reason mse is said to have be better probabilistic interpretation.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.