ruby/tensorflow_privacy
1
0
Fork 0
forked from 626_privacy/tensorflow_privacy
Code Pull requests Activity

Add link to paper on Renyi Differential Privacy.

Browse source 
PiperOrigin-RevId: 267412177
This commit is contained in:
Steve Chien 2019-09-05 11:15:08 -07:00 committed by A. Unique TensorFlower
parent bb89ba6963
commit 0776ed124b
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
tutorials/README.md
View file

@ -76,6 +76,9 @@ compute the privacy guarantee) are:
* `noise_multiplier` : The noise_multiplier from your parameters above. * `noise_multiplier` : The noise_multiplier from your parameters above.
* `steps` : The number of global steps taken. * `steps` : The number of global steps taken.
A detailed writeup of the theory behind the computation of epsilon and delta
is available at https://arxiv.org/abs/1908.10530.
## Expected Output ## Expected Output
When the `mnist_dpsgd_tutorial.py` script is run with the default parameters, When the `mnist_dpsgd_tutorial.py` script is run with the default parameters,