626_privacy/tensorflow_privacy
2
0
Fork 1
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions
188 commits 2 branches 0 tags 3.1 MiB
Commit graph

113 commits

Author SHA1 Message Date
Nicolas Papernot
c7ca8092fb Introduce vectorized DP optimizer 
PiperOrigin-RevId: 262414086
 2019-08-08 12:56:28 -07:00
Zachary Garrett
c08f3ebdc7 Workaround until the new bolt_on module is integrated into the rest of the TF Privacy build system. 
PiperOrigin-RevId: 261222062
 2019-08-01 16:32:32 -07:00
A. Unique TensorFlower
9fe5e91de4 Merge pull request #53 from georgianpartners:master 
PiperOrigin-RevId: 260990063
 2019-07-31 13:44:12 -07:00
npapernot
12dc0b9497 last typo 2019-07-31 20:40:30 +00:00
Christopher Choquette Choo
4bd0ad482a Refactoring bolton to bolt_on from package refactor for comments + strings. 2019-07-31 10:55:25 -04:00
Christopher Choquette Choo
c0bd19365b Refactoring bolton package to bolt_on only in code usages. 2019-07-31 10:52:41 -04:00
npapernot
223f2cc640 trailing spaces 2019-07-30 22:00:16 +00:00
npapernot
cd0ff6d299 indent 2019-07-30 21:53:53 +00:00
Christopher Choquette Choo
2065f2b16a Code style and documentation changes. 2019-07-30 15:12:22 -04:00
npapernot
fb12ee047f more lint 2019-07-29 22:35:13 +00:00
npapernot
d29f31ec44 more lint 2019-07-29 22:33:30 +00:00
npapernot
f470ae4a7c more lint 2019-07-29 22:30:45 +00:00
npapernot
801e6eef1c more lint 2019-07-29 22:22:52 +00:00
npapernot
b1f1c47cae more lint 2019-07-29 22:15:52 +00:00
npapernot
ed93cf6f44 more lint 2019-07-29 22:09:21 +00:00
npapernot
32c76e588a more lint 2019-07-29 22:00:53 +00:00
npapernot
ddf17c9091 more lint 2019-07-29 21:55:14 +00:00
npapernot
f06443d50e more lint 2019-07-29 21:43:19 +00:00
npapernot
33c3f058ac conflicts in models 2019-07-29 21:34:02 +00:00
npapernot
034ae8fea4 conflicts in models test 2019-07-29 21:29:03 +00:00
npapernot
d10d7b0148 conflicts in opt test 2019-07-29 21:27:54 +00:00
npapernot
19ce36777d format fixes 2019-07-29 21:20:40 +00:00
Yilei Yang
c14a546440 Explicitly mark Python binaries/tests with python_version = "PY2". 
PiperOrigin-RevId: 260525846
 2019-07-29 10:16:54 -07:00
Christopher Choquette Choo
71c4a11eb9 Fixing new pylint errors. 2019-07-27 14:14:05 -04:00
Christopher Choquette Choo
92f97ae32c Fixing missing args. 2019-07-27 13:54:19 -04:00
npapernot
8974a95b9a more fixes 2019-07-25 16:13:32 +00:00
npapernot
8e6bcf9b4a many fixes 2019-07-25 15:37:54 +00:00
npapernot
fe90e3c596 readme fixes - more 2019-07-25 14:44:21 +00:00
npapernot
d0ef1b380c readme fixes 2019-07-25 14:38:37 +00:00
A. Unique TensorFlower
5cd2439401 Remove calls to _dp_sum_query.set_batch_size in dp_optimizer.py, as no method with that name exists for objects of class QueryWithLedger. 
PiperOrigin-RevId: 259858031
 2019-07-24 18:08:35 -07:00
Christopher Choquette Choo
968ea70060 Fixing typos. 2019-07-22 11:30:55 -04:00
Christopher Choquette Choo
7785436cf3 Minor changes to README 2019-07-22 11:30:29 -04:00
Christopher Choquette Choo
0082c9ba76 Minor doc change and adding README file explaining Bolton Method. 2019-07-22 11:27:53 -04:00
jvmancuso
3072c86c79 find nest module based on TF version for quantile_adaptive_clip_sum_query.py 2019-07-20 10:43:48 -04:00
Christopher Choquette Choo
c05c2aa0d4 Ensuring pylint is 10/10 2019-07-18 15:04:35 -04:00
A. Unique TensorFlower
98723b9c3a Added rdp_accountant dependency to privacy/BUILD. 
PiperOrigin-RevId: 258657061
 2019-07-17 15:44:16 -07:00
Christopher Choquette Choo
b03eb6914b Code review changes: Fixed doc string spacing, copyrighting, and changed the jupyter file to a python script. 2019-07-16 10:33:57 -04:00
Galen Andrew
973a1759aa Remove unused global_state reference from initial_sample_state. 
global_state is never used in any of our existing DPQueries, and we don't have any compelling use case.

PiperOrigin-RevId: 255480537
 2019-06-27 14:37:49 -07:00
Nicolas Papernot
6171474465 harmonize analysis parameters with current DPSGD API 
PiperOrigin-RevId: 255080643
 2019-06-25 17:06:01 -07:00
Christopher Choquette Choo
3080b654b5 Minor changes to function arguments 2019-06-19 11:18:42 -04:00
Christopher Choquette Choo
b120d9c5d8 Changes for pylint. 2019-06-19 11:14:02 -04:00
Christopher Choquette Choo
56e16f0a15 Minor changes + tutorial 2019-06-19 11:04:18 -04:00
Christopher Choquette Choo
f41be2c598 Bolton implementation and unit tests. Has two pre-implemented loss functions. 2019-06-19 10:46:30 -04:00
Christopher Choquette Choo
ed7fa73a99 Update Huber loss regularization term and some small changes across loss parameters. 2019-06-17 14:46:04 -04:00
Christopher Choquette Choo
935d6e8480 Bolton created as optimizer with context manager usage. 
Unit tests included.
Additional loss functions TBD.
 2019-06-17 13:25:30 -04:00
Christopher Choquette Choo
ec18db5ec5 Working bolton model without unit tests. 
-- moving to Bolton Optimizer
Model is now just a convenient wrapper and example for users.
Optimizer holds ALL Bolton privacy requirements.
Optimizer is used as a context manager, and must be passed the model's layers.
Unit tests incomplete, committing for visibility into the design.
 2019-06-13 01:01:31 -04:00
Christopher Choquette Choo
751eaead54 Working bolton model without unit tests. 
-- update to include pull request changes
changes include:
parameter renaming,
changing to mixin,
moving model to compile,
additional tests,
fixing huber loss
 2019-06-10 16:11:47 -04:00
Christopher Choquette Choo
5f46927747 Working bolton model without unit tests. 2019-06-05 17:06:02 -04:00
Galen Andrew
d5dcfec745 Remove set_denominator functions from DPQuery and make QueryWithLedger easier to use. 
set_denominator was added so that the batch size doesn't need to be specified before constructing the optimizer, but it breaks the DPQuery abstraction. Now the optimizer uses a GaussianSumQuery instead of GaussianAverageQuery, and normalization by batch size is done inside the optimizer.

Also instead of creating all DPQueries with a PrivacyLedger and then wrapping with QueryWithLedger, it is now sufficient to create the queries with no ledger and QueryWithLedger will construct the ledger and pass it to all inner queries.

PiperOrigin-RevId: 251462353
 2019-06-04 10:14:32 -07:00
Galen Andrew
7636945566 Cast to ensure record of NoPrivacyAverageQuery is float for compatibility with sample_state. 
PiperOrigin-RevId: 249909614
 2019-05-24 15:28:39 -07:00