The discrepancy between DARTS and ENAS for RNN cell searching

[cocovoc]

Hi,everyone
I got confused when I read the code.
In rnn/model_search.py line 28

ch = masked_states.view(-1, self.nhid).mm(self._Ws[i]).view(i+1, -1, 2*self.nhid)
It seems that hidden states of all predecessor share the same matrix: H_{3} = WH{0}+WH{1}+W*H{2}
Actually, I think right computation is H_{3} = W_{0,3}*H{0}+W_{1,3}*H{1}+W_{2,3}*H{2}.

Any knows the reason why author uses the same matrix? just only for saving memory?