Why is it easier to incorporate arbitrary features into discriminative models?

by matt   Last Updated April 15, 2019 09:19 AM

It is often stated, that when arbitrary features are implied, generative models (e.g. Naive Bayes) are a lesser fit than discriminative ones. What are the reasons for that?



Related Questions


Updated June 16, 2017 10:19 AM

Updated November 25, 2017 11:19 AM

Updated October 05, 2018 13:19 PM

Updated July 03, 2018 12:19 PM

Updated October 04, 2018 02:19 AM