diff options
author | Yuchen Pei <me@ypei.me> | 2019-03-17 09:14:45 +0100 |
---|---|---|
committer | Yuchen Pei <me@ypei.me> | 2019-03-17 09:14:45 +0100 |
commit | ef11d59204d46388048ada5cd1cc5f850c960549 (patch) | |
tree | 43d72d9098e3cea4a31a5cb26d84e7a06cb7a492 /posts | |
parent | 222df0225755023cc596556f5310ca164e9553ee (diff) |
minor
Diffstat (limited to 'posts')
-rw-r--r-- | posts/2019-03-13-a-tail-of-two-densities.md | 4 |
1 files changed, 2 insertions, 2 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 f7d6c91..533835d 100644 --- a/posts/2019-03-13-a-tail-of-two-densities.md +++ b/posts/2019-03-13-a-tail-of-two-densities.md @@ -26,7 +26,7 @@ as well as the effect of mixing mechanisms, by presenting the subsampling theore (a.k.a. amplification theorem). In [Part 2](/posts/2019-03-14-great-but-manageable-expectations.html), I discuss the Rényi differential privacy, corresponding to -the Rényi divergence, a study of the moment generating functions the +the Rényi divergence, a study of the moment generating functions of the divergence between probability measures to derive the tail bounds. Like in Part 1, I prove a composition theorem and a subsampling theorem. @@ -591,7 +591,7 @@ Legendre transformation). When $\xi$ is standard normal, we get (6.5). $\square$ **Remark**. We will use the Chernoff bound extensively in the -second part of this post when considering Renyi differential privacy. +second part of this post when considering Rényi differential privacy. **Claim 9**. The Gaussian mechanism on a query $f$ is $(\epsilon, \delta)$-dp, where |