Stability of a regularized Newton method with two potentials
Boushra Abbas

TL;DR
This paper investigates the stability of a regularized Newton method with two potentials in Hilbert spaces, focusing on its robustness and implications for numerical algorithms involving structured monotone operators.
Contribution
It introduces a stability analysis for a regularized Newton method with two potentials, allowing the regularization coefficient to vary and linking to combined forward-backward and Newton algorithms.
Findings
Stability results for the regularized Newton method are established.
The regularization coefficient can be of bounded variation.
Implications for numerical algorithms combining forward-backward and Newton methods.
Abstract
In a Hilbert space setting, we study the stability properties of the regularized continuous Newton method with two potentials, which aims at solving inclusions governed by structured monotone operators. The Levenberg-Marquardt regularization term acts in an open loop way. As a byproduct of our study, we can take the regularization coefficient of bounded variation. These stability results are directly related to the study of numerical algorithms that combine forward-backward and Newton's methods.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
