aboutsummaryrefslogtreecommitdiff
path: root/posts
diff options
context:
space:
mode:
authorYuchen Pei <me@ypei.me>2019-03-14 11:22:31 +0100
committerYuchen Pei <me@ypei.me>2019-03-14 11:22:31 +0100
commit59a09ee80a50c4a07aeda9cf6526a67534d5cc54 (patch)
tree4e85bb3a4a8e6cf89219c8d6269b2d8517a8b3d7 /posts
parent83b0953fa85b4c7a11edc4bc75b205f38e434a75 (diff)
minor
Diffstat (limited to 'posts')
-rw-r--r--posts/2019-03-14-great-but-manageable-expectations.md2
1 files changed, 1 insertions, 1 deletions
diff --git a/posts/2019-03-14-great-but-manageable-expectations.md b/posts/2019-03-14-great-but-manageable-expectations.md
index adce24f..95cf5f2 100644
--- a/posts/2019-03-14-great-but-manageable-expectations.md
+++ b/posts/2019-03-14-great-but-manageable-expectations.md
@@ -522,7 +522,7 @@ The DP-SGD is implemented in [TensorFlow
Privacy](https://github.com/tensorflow/privacy). In the following I
discuss the package in the current state (2019-03-11). It is divided
into two parts: `optimizers` which implements the actual differentially
-private algorithm, and `analysis` which computes the privacy guarantee.
+private algorithm, and [`analysis`](https://github.com/tensorflow/privacy/tree/master/privacy/analysis) which computes the privacy guarantee.
The `analysis` parts implements a privacy ledger that \"keeps a record
of all queries executed over a given dataset for the purpose of