Comments (4)
Hi DmsKinson,
Thanks for the question. We divide the batchsize because the noise is added to the average of gradients instead of the sum of gradients. This can prevent numerical overflow when using half precision and the batchsize is large and (although in this code we use full precision). You can find the gradient averaging operations at here.
from differentially-private-deep-learning.
Thanks for you response. So does it mean that the sensitivity of the gradient is clip*batchisize?
from differentially-private-deep-learning.
Without average, the sensitivity is exactly the clip as in the DP-SGD paper. With average, the sensitivity is clip/batchsize.
from differentially-private-deep-learning.
I see. Thanks for your answer.
from differentially-private-deep-learning.
Related Issues (6)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from differentially-private-deep-learning.