diff options
author | Yuchen Pei <me@ypei.me> | 2019-03-19 16:20:14 +0100 |
---|---|---|
committer | Yuchen Pei <me@ypei.me> | 2019-03-19 16:20:14 +0100 |
commit | ac8979f6770d2c1ed79b680fc720cbefd8d588c7 (patch) | |
tree | 01ac6536f0853253b48b0e6d77d6b214a6ef512a /posts | |
parent | 01f02143bbb94e8d0b873daa0df087db4e488b22 (diff) |
minor
Diffstat (limited to 'posts')
-rw-r--r-- | posts/2019-03-13-a-tail-of-two-densities.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/posts/2019-03-13-a-tail-of-two-densities.md b/posts/2019-03-13-a-tail-of-two-densities.md index 460364a..f3e409c 100644 --- a/posts/2019-03-13-a-tail-of-two-densities.md +++ b/posts/2019-03-13-a-tail-of-two-densities.md @@ -8,7 +8,7 @@ comments: true This is Part 1 of a two-part post where I give an introduction to differential privacy, which is a study of tail bounds of the divergence between probability measures, with the end goal of applying it to stochastic -gradient descent. +gradient descent. I start with the definition of $\epsilon$-differential privacy (corresponding to max divergence), followed by |