tensorflow_privacy/privacy/optimizers
Galen Andrew 9106a04e2c Use PrivacyLedger for privacy accounting.
Prior to this change the PrivacyLedger is running to keep a log of private queries, but the ledger is not actually used to compute the (epsilon, delta) guarantees. This CL adds a function to compute the RDP directly from the ledger.

Note I did verify that the tutorial builds and runs with the changes and for the first few iterations prints the same epsilon values as before the change.

PiperOrigin-RevId: 241063532
2019-03-29 15:31:32 -07:00
..
__init__.py Project import generated by Copybara. 2018-12-18 15:44:04 -08:00
dp_optimizer.py Use PrivacyLedger for privacy accounting. 2019-03-29 15:31:32 -07:00
dp_optimizer_eager_test.py Cleanup directory structure, add top-level imports and add normalized_query. 2019-03-25 10:21:04 -07:00
dp_optimizer_test.py Use PrivacyLedger for privacy accounting. 2019-03-29 15:31:32 -07:00