In the DAN paper, you say "we can automatically select the MMD penalty parameter(lambda) on a validation set by jointly assessing the test errors of the source classifier and the two-sample classifier", and in the code you just set the parameter=1. How to understand this?
In the DAN paper, you say "we can automatically select the MMD penalty parameter(lambda) on a validation set by jointly assessing the test errors of the source classifier and the two-sample classifier", and in the code you just set the parameter=1. How to understand this?