From 0082c9ba7682ff2bb389dcfe800e973652642afd Mon Sep 17 00:00:00 2001
From: Christopher Choquette Choo <choquette.christopher@gmail.com>
Date: Mon, 22 Jul 2019 11:27:53 -0400
Subject: [PATCH 1/3] Minor doc change and adding README file explaining Bolton
 Method.

---
 privacy/bolton/README.md | 56 ++++++++++++++++++++++++++++++++++++++++
 privacy/bolton/models.py |  2 +-
 2 files changed, 57 insertions(+), 1 deletion(-)
 create mode 100644 privacy/bolton/README.md

diff --git a/privacy/bolton/README.md b/privacy/bolton/README.md
new file mode 100644
index 0000000..ad3c141
--- /dev/null
+++ b/privacy/bolton/README.md
@@ -0,0 +1,56 @@
+# Bolton Module
+
+This module contains source code for the Bolton method. This method is a subset
+of methods used in the ensuring privacy in machine learning that leverages
+additional assumptions to provide a new way of approaching the privacy 
+guarantees.
+
+## Bolton Description
+
+This method uses 4 key steps to achieve privacy guarantees:
+  1. Adds noise to weights after training (output perturbation).
+  2. Projects weights to R after each batch
+  3. Limits learning rate
+  4. Use a strongly convex loss function (see compile)
+
+For more details on the strong convexity requirements, see:
+Bolt-on Differential Privacy for Scalable Stochastic Gradient
+Descent-based Analytics by Xi Wu et al.
+
+### Why Bolton?
+
+The major difference for the Bolton method is that it injects noise post model
+convergence, rather than noising gradients or weights during training. This 
+approach requires some additional constraints listed in the Description. 
+Should the use-case and model satisfy these constraints, this is another
+approach that can be trained to maximize utility while maintaining the privacy.
+The paper describes in detail the advantages and disadvantages of this approach 
+and its results compared to some other methods, namely noising at each iteration
+and no noising.
+
+## Tutorials
+
+This module has a tutorial that can be found in the root tutorials directory, 
+under boton_tutorial.py.
+
+## Contribution
+
+This module was initially contributed by Georgian Partners with the hope of 
+growing the tensorflow/privacy library. There are several rich use cases for 
+delta-epsilon privacy in machine learning, some of which can be explored here:
+https://medium.com/apache-mxnet/epsilon-differential-privacy-for-machine-learning-using-mxnet-a4270fe3865e
+https://arxiv.org/pdf/1811.04911.pdf
+
+## Contacts
+
+In addition to the maintainers of tensorflow/privacy listed in the root 
+README.md, please feel free to contact members of Georgian Partners. In 
+particular,
+
+* Georgian Partners (@georgianpartners)
+* Ji Chao Zhang (@Jichaogp)
+* Christopher Choquette (@cchoquette)
+
+## Copyright
+
+Copyright 2019 - Google LLC
diff --git a/privacy/bolton/models.py b/privacy/bolton/models.py
index 2c5c08a..634f94c 100644
--- a/privacy/bolton/models.py
+++ b/privacy/bolton/models.py
@@ -38,7 +38,7 @@ class BoltonModel(Model):  # pylint: disable=abstract-method
 
   For more details on the strong convexity requirements, see:
   Bolt-on Differential Privacy for Scalable Stochastic Gradient
-  Descent-based Analytics by Xi Wu et. al.
+  Descent-based Analytics by Xi Wu et al.
   """
 
   def __init__(self,

From 7785436cf3550821c4fab60e0c9517ee6678a90d Mon Sep 17 00:00:00 2001
From: Christopher Choquette Choo <choquette.christopher@gmail.com>
Date: Mon, 22 Jul 2019 11:30:29 -0400
Subject: [PATCH 2/3] Minor changes to README

---
 privacy/bolton/README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/privacy/bolton/README.md b/privacy/bolton/README.md
index ad3c141..aa140e5 100644
--- a/privacy/bolton/README.md
+++ b/privacy/bolton/README.md
@@ -1,6 +1,6 @@
-# Bolton Module
+# Bolton SubPpckage
 
-This module contains source code for the Bolton method. This method is a subset
+This package contains source code for the Bolton method. This method is a subset
 of methods used in the ensuring privacy in machine learning that leverages
 additional assumptions to provide a new way of approaching the privacy 
 guarantees.
@@ -30,12 +30,12 @@ and no noising.
 
 ## Tutorials
 
-This module has a tutorial that can be found in the root tutorials directory, 
+This package has a tutorial that can be found in the root tutorials directory, 
 under boton_tutorial.py.
 
 ## Contribution
 
-This module was initially contributed by Georgian Partners with the hope of 
+This package was initially contributed by Georgian Partners with the hope of 
 growing the tensorflow/privacy library. There are several rich use cases for 
 delta-epsilon privacy in machine learning, some of which can be explored here:
 https://medium.com/apache-mxnet/epsilon-differential-privacy-for-machine-learning-using-mxnet-a4270fe3865e

From 968ea70060bc459cfe9426e97d9b69d0719b722c Mon Sep 17 00:00:00 2001
From: Christopher Choquette Choo <choquette.christopher@gmail.com>
Date: Mon, 22 Jul 2019 11:30:55 -0400
Subject: [PATCH 3/3] Fixing typos.

---
 privacy/bolton/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/privacy/bolton/README.md b/privacy/bolton/README.md
index aa140e5..95d6b68 100644
--- a/privacy/bolton/README.md
+++ b/privacy/bolton/README.md
@@ -1,4 +1,4 @@
-# Bolton SubPpckage
+# Bolton Subpackage
 
 This package contains source code for the Bolton method. This method is a subset
 of methods used in the ensuring privacy in machine learning that leverages