Yu-Xiang Wang

@googlebot I signed it! > On Aug 14, 2019, at 4:59 PM, googlebot wrote: > > @googlebot I signed it!

Good question. The "group_size" parameter there was part of the initial design. It's not implemented yet besides the default value of 1. In particular, supporting group composition for a generic...

I will not close this for now because this is to be solved by adding a "TransformerZoo.GroupComposition"

hmmm... this seems to be a windows problem. I haven't tested it on windows. We will look into it. For now, could you try a local installation using the master...

This is an interesting case. "bounded" were used when there is a natural bounded range, and I implemented a doubling trick to get the right bound for some of the...

Thanks for the issue, Ryan! 'dp_bank.get_logdelta_ana_gaussian' has two arguments. the first should be sigma. the second should be the desired epsilon. In your implementation, it seems that you passed eps...

hmmmm... sorry it took me a long while to get back to you on this. I don't yet know the root cause of this, but it might be due the...

Short answers: AutoDP allows privacy amplification by choosing a random subset. Both autodp and tf.privacy have implemented the version for poisson sampling (including each data point with a fixed probability...

The bottomline is that: If your algorithm is actually doing a random subset with a fixed cardinality, then using the Poisson sampling bounds to account for privacy would be the...

Thanks for trying it out! ```transformer_zoo.Composition``` uses RDP for composition by default. At the moment, our partial support of fDP does not allow generic conversion of fDP to RDP yet....