necludov / group-sparsity-sbp Goto Github PK

In paper, the final loss function is presented in equation (12),
the estimated expected log-likelihood through SGVB and KL divergence.

It seems that the SBP layer only takes KL divergence into account, why don't we need to deal with the expected log-likelihood term?

Is the log likelihood included as our objective function?

The paper mentions that for VGG-like training, a pretrained model was used. Could a link be provided for the checkpoint file of the pretrained model so the vgglike-sbp.py experiment can be replicated independently?

Hi, I try to re-implement your paper on pytorch. I changed your erfcx function to adapt pytorch tensor. After compared to the values of special.erfcx(x), the average absolute error is approximate 2.11-08, and average relative error is approximate 3.91e-08, both are much larger than your erfcx approximation. Could this be a problem?

Thanks ,
Shangqian