Closed ghost closed 3 years ago
1) draw_sample is only for drawing samples, which is not necessary if you just want to use the adaptive loss. 2) The input to the loss function is assumed to be the difference between y and \mu. You'll want to predict a mu and then subtract it from the datapoint labels you're trying to regress to.
Thanks for your reply!
Hi Jonathan,
Thanks for your paper and code, they are amazing. May I ask several questions?
Thanks for your help.