Is this a one-layer version ?

[Yihan-zz]

Thanks for your works ! I read the file 'pubmed_Mix_sampleA.py' and I found that it only sample once which means the model just has one layer. But the paper said the result is test on two-layer models. Is there anything I miss ?

[matenure]

It is a two-layer version. But for the bottom layer, we pre-compute the $AX$ as we explained in the paper, so we just did sampling for the top layer.