Mengye Ren

That's right. The purpose is to build a computational graph to calculate the gradients to `ex_wts_a`

Eq. 30 in the Appendix B relies on the fact that we are taking gradients when ex_wts_a is 0. On Thu, Jul 23, 2020 at 9:27 AM zhegeliang2 wrote: >...

Hi, the clean validation set is split from the training set.