I ran the MNIST example provided on github with different choices of argument c
(max-per-sample-grad_norm
) which determines the max_grad_norm
parameter in privacy_engine
. The other arguments are the set to their default values. However, the output DP parameter epsilon
does not change with different values of max_grad_norm
. The screenshots of the output are provided below.
I am very confused because I would expect that epsilon
would be smaller for smaller max_grad_norm
according to the theory of DP. Is there anything wrong with the code? Thanks.
Commands:
python mnist.py -c 1
python mnist.py -c 10
Results: