Trajectory convergence and $o(t^{-2})$ rates for Nesterov accelerated primal-dual dynamics without Lipschitz gradient assumption
Xin He, Nan-Jing Hang, Yi-Bin Xiao, Ya-Ping Fang

TL;DR
This paper proves convergence and improved rates for a Nesterov accelerated primal-dual system solving linearly constrained problems without requiring Lipschitz continuity of the gradient, extending previous results.
Contribution
It establishes convergence and $o(t^{-2})$ rates for the primal-dual dynamics in finite dimensions without Lipschitz gradient assumptions, including the critical case $oldsymbol{ ext{α=3}}$.
Findings
Trajectory converges to a primal-dual solution for $oldsymbol{ ext{α≥3}}$ without Lipschitz gradient.
Improved $o(t^{-2})$ convergence rates for objective residual and feasibility when $oldsymbol{ ext{α>3}}$.
First results on convergence of accelerated primal-dual dynamics for the critical case $oldsymbol{ ext{α=3}}$.
Abstract
We consider the Nesterov accelerated primal-dual dynamical system \[ \begin{cases} \ddot{x}(t)+\dfrac{\alpha}{t}\dot{x}(t) +\nabla f(x(t)) +A^\top\bigl(\lambda(t)+\theta t\dot{\lambda}(t)\bigr)+\beta A^\top(Ax(t)-b)=0,\\[0.6em] \ddot{\lambda}(t)+\dfrac{\alpha}{t}\dot{\lambda}(t) -\bigl(A(x(t)+\theta t\dot{x}(t))-b\bigr)=0, \end{cases} \] which is linked to the linearly constrained optimization problem where and is convex and continuously differentiable. In a Hilbert framework, the weak convergence of its trajectory was established by Bo\c{t} and Nguyen (J. Differential Equations, 303:369--406, 2021) under and the Lipschitz continuity assumption on . In this paper, we prove in finite-dimensional spaces that the trajectory converges to a primal-dual solution for , without assuming Lipschitz…
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.
