Mehdi Amian

Thank you for reply. I really appreciate it. I get your point. Reservation is that it seems to me that the idea of clipping gradient per individual (input sample) is...

You are absolutely right. In fact, when the number of minibatch is different than that of microbatch, the algorithm is not supposed to look at individual gradients within a microbatch...

Hi Peter, Thank you so much for the reply. I really appreciate it. Adjustments like clipping gradient. I am interested in calculating the privacy budget caused by just clipping gradient,...

Thanks again Peter. So, if the clip contributes to no privacy, why should we keep it? I mean, we could avoid the clip (if it offers no privacy) and reach...

Thank you so much Peter. It's helpful.

Does the current algorithm (the "rdp_accountant" code) of calculating delta and epsilon support other forms of clipping rather than that is proposed by Abadi? I mean, keeping noise addition (as...

I see. Thanks a lot for elaboration.