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

Regularization for Newton's methods #1126

Open

kbarros opened this issue Jan 21, 2025 · 0 comments

kbarros commented Jan 21, 2025 •

edited

Loading

Here is an interesting variant of Newton's method with regularization: https://www.konstmish.com/publication/21_newton/.

According to the abstract:

Our method is the first variant of Newton’s method [for convex objects with Lipschitz Hessian] that has both cheap iterations [line search not required] and provably fast global convergence [speed of cubic Newton method].

The implementation of this regularization looks relatively straightforward, so I wonder if it could be incorporated into Optim.jl?

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