Computes RDP of the Tree Aggregation Protocol for Gaussian Mechanism.
tf_privacy.compute_rdp_tree_restart(
noise_multiplier: float,
steps_list: Union[int, Collection[int]],
orders: Union[float, Collection[float]]
) -> Union[float, Collection[float]]
This function implements the accounting when the tree is restarted at every
epoch. See appendix D of
"Practical and Private (Deep) Learning without Sampling or Shuffling"
https://arxiv.org/abs/2103.00039
Args |
noise_multiplier
|
A non-negative float representing the ratio of the
standard deviation of the Gaussian noise to the l2-sensitivity of a single
contribution (a leaf node), which is usually set in
TreeCumulativeSumQuery and TreeResidualSumQuery from
dp_query.tree_aggregation_query .
|
steps_list
|
A scalar or a list of non-negative intergers representing the
number of steps per epoch (between two restarts).
|
orders
|
An array (or a scalar) of RDP orders.
|
Returns |
The RDPs at all orders. Can be np.inf .
|