Jean-Marc Gervais
Jean-Marc Gervais
My doubts seem to be justified, see the [fixed issue I registered about the clone of this script for PyTorch framework](https://github.com/facebookresearch/pytorch-dp/commit/3bbed59a57f22d4c4db6147617c5be52cb54d461). Someone to confirm (or invalidate) this ? (@ffuuugor ?...
Hi @carlodavid012. "Classical" (epsilon, delta)-DP is our purpose here, but (alpha, epsilon)-Rényi DP has to be used to compute a tighter bound than the one get by classical DP composition....
In addition, there is a greate explanation here: [https://github.com/tensorflow/privacy/tree/master/tutorials/walkthrough](https://github.com/tensorflow/privacy/tree/master/tutorials/walkthrough) Regards.