Regularized Newton Methods for Monotone Variational Inequalities with H\"older Continuous Jacobians
Chengchang Liu, Luo Luo

TL;DR
This paper introduces regularized Newton methods tailored for monotone variational inequalities with H"older continuous Jacobians, achieving improved iteration complexity based on the H"older parameter.
Contribution
It develops both parameter-dependent and universal regularized Newton methods with new iteration complexity bounds for solving these inequalities.
Findings
Achieves $oxed{ ext{O}( ext{}\epsilon^{-2/(2+ u)})}$ iteration complexity with known H"older parameter.
Proposes a universal method with $oxed{ ext{O}( ext{}\epsilon^{-4/(3(1+ u))})}$ complexity when the parameter is unknown.
Extends Newton-type methods to handle H"older continuous Jacobians effectively.
Abstract
This paper considers the problems of solving monotone variational inequalities with H\"older continuous Jacobians. By employing the knowledge of H\"older parameter , we propose the -regularized extra-Newton method within at most iterations to obtain an -accurate solution. In the case of is unknown, we propose the universal regularized extra-Newton method within iteration complexity.
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.
Taxonomy
TopicsAdvanced Optimization Algorithms Research · Optimization and Variational Analysis · Topology Optimization in Engineering
