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

Minor fix of tree aggregation accounting docstring.

Browse source 
PiperOrigin-RevId: 426398939
This commit is contained in:
Zheng Xu 2022-02-04 07:31:35 -08:00 committed by A. Unique TensorFlower
parent c3e7f08fa5
commit 2fe51d2eeb
1 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
tensorflow_privacy/privacy/analysis/tree_aggregation_accountant.py
View file

@ -99,8 +99,8 @@ def compute_rdp_tree_restart(
Args:
noise_multiplier: A non-negative float representing the ratio of the
standard deviation of the Gaussian noise to the l2-sensitivity of the
function to which it is added, which is usually set in
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
@ -292,8 +292,8 @@ def compute_rdp_single_tree(
Args:
noise_multiplier: A non-negative float representing the ratio of the
standard deviation of the Gaussian noise to the l2-sensitivity of the
function to which it is added, which is usually set in
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`.
total_steps: Total number of steps (leaf nodes in tree aggregation).
@ -354,8 +354,8 @@ def compute_zcdp_single_tree(
Args:
noise_multiplier: A non-negative float representing the ratio of the
standard deviation of the Gaussian noise to the l2-sensitivity of the
function to which it is added, which is usually set in
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`.
total_steps: Total number of steps (leaf nodes in tree aggregation).