Attend the Women in ML Symposium on December 7 Register now

tf_privacy.compute_rdp_tree_restart

Stay organized with collections Save and categorize content based on your preferences.

Computes RDP of the Tree Aggregation Protocol for Gaussian Mechanism.

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

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.

The RDPs at all orders. Can be np.inf.