English

A Continuous-Time Perspective on Global Acceleration for Monotone Equation Problems

Optimization and Control 2024-07-22 v7 Computational Complexity Data Structures and Algorithms

Abstract

We propose a new framework to design and analyze accelerated methods that solve general monotone equation (ME) problems F(x)=0F(x)=0. Traditional approaches include generalized steepest descent methods and inexact Newton-type methods. If FF is uniformly monotone and twice differentiable, these methods achieve local convergence rates while the latter methods are globally convergent thanks to line search and hyperplane projection. However, a global rate is unknown for these methods. The variational inequality methods can be applied to yield a global rate that is expressed in terms of F(x)\|F(x)\| but these results are restricted to first-order methods and a Lipschitz continuous operator. It has not been clear how to obtain global acceleration using high-order Lipschitz continuity. This paper takes a continuous-time perspective where accelerated methods are viewed as the discretization of dynamical systems. Our contribution is to propose accelerated rescaled gradient systems and prove that they are equivalent to closed-loop control systems. Based on this connection, we establish the properties of solution trajectories. Moreover, we provide a unified algorithmic framework obtained from discretization of our system, which together with two approximation subroutines yields both existing high-order methods and new first-order methods. We prove that the pthp^{th}-order method achieves a global rate of O(kp/2)O(k^{-p/2}) in terms of F(x)\|F(x)\| if FF is pthp^{th}-order Lipschitz continuous and the first-order method achieves the same rate if FF is pthp^{th}-order strongly Lipschitz continuous. If FF is strongly monotone, the restarted versions achieve local convergence with order pp when p2p \geq 2. Our discrete-time analysis is largely motivated by the continuous-time analysis and demonstrates the fundamental role that rescaled gradients play in global acceleration for solving ME problems.

Keywords

Cite

@article{arxiv.2206.04770,
  title  = {A Continuous-Time Perspective on Global Acceleration for Monotone Equation Problems},
  author = {Tianyi Lin and Michael. I. Jordan},
  journal= {arXiv preprint arXiv:2206.04770},
  year   = {2024}
}

Comments

Accepted by Communications in Optimization Theory; 29 Pages; Fix the inaccurate statement in Remark 2.7 and some typos

R2 v1 2026-06-24T11:45:45.738Z