New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

DP linear regression #22

Open

LaRiffle opened this issue Mar 31, 2023 · 0 comments

Labels

Member

LaRiffle commented Mar 31, 2023

Problem

Linear regression can be solved by gradient descent, using the analogy of a 1 hidden layer neural network, see for instance : https://www.cs.cmu.edu/afs/cs.cmu.edu/academic/class/15381-s06/www/nn.pdf

Opacus is a Python library implementing neural network regression with DP-stochastic gradient descent

If we wrap Opacus in R, we should be able to propose an Linear regression solver with DP

LaRiffle added the type/feature label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment