Asymptotic for a second order evolution equation with convex potential and vanishing damping term
Ramzi May

TL;DR
This paper presents a new method to analyze the asymptotic behavior of solutions to a second order convex potential evolution equation with vanishing damping, improving convergence rate results.
Contribution
It introduces an alternative proof for weak convergence and refines the convergence rate of the potential function to its minimum.
Findings
Solutions weakly converge as t approaches infinity.
Improved rate of convergence for the potential function.
Method offers a different perspective from previous work.
Abstract
In this short note, we recover by a different method the new result due to Attouch, Peyrouqet and Redont concerning the weak convergence as of solutions to the second order differential equation \[ x^{\prime\prime}(t)+\frac{K}{t}x^{\prime}(t)+\nabla\Phi(x(t))=0, \] where and is a smooth convex function defined on an Hilbert Space Moreover, we improve slightly their result on the rate of convergence of
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.
