A. Unique TensorFlower 93c7e54327 Sparsity Preserving DP-SGD in TF Privacy ... Add function to merge varname_to_contribution_count_fn maps from different layers. See https://research.google/blog/sparsity-preserving-differentially-private-training/ for more details on the algorithm. PiperOrigin-RevId: 664906202		2024-08-19 11:44:43 -07:00
..
privacy	Sparsity Preserving DP-SGD in TF Privacy	2024-08-19 11:44:43 -07:00
v1	Internal Code Change	2023-08-15 11:42:02 -07:00
.bazelversion	Add .bazelversion file.	2022-05-11 14:14:48 -07:00
__init__.py	Make compute_dp_sgd_privacy_statement visible.	2023-03-28 12:43:21 -07:00
BUILD	Internal Code Change	2023-08-15 11:42:02 -07:00
version.py	Increase version to 0.9.0 after splitting off TF empirical privacy package.	2024-02-08 12:22:59 -08:00