From 12dc0b9497899f11cf9fe466d6c468ce46147d5d Mon Sep 17 00:00:00 2001 From: npapernot Date: Wed, 31 Jul 2019 20:40:30 +0000 Subject: [PATCH] last typo --- privacy/bolt_on/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/privacy/bolt_on/README.md b/privacy/bolt_on/README.md index 77d79d1..3d55977 100644 --- a/privacy/bolt_on/README.md +++ b/privacy/bolt_on/README.md @@ -12,7 +12,7 @@ This method uses 4 key steps to achieve privacy guarantees: 2. Projects weights to R, the radius of the hypothesis space, after each batch. This value is configurable by the user. 3. Limits learning rate - 4. Use a strongly convex loss function (see compile) + 4. Uses a strongly convex loss function (see compile) For more details on the strong convexity requirements, see: Bolt-on Differential Privacy for Scalable Stochastic Gradient