Metraipolis › archive › dc_179f43a1db4e

Optimal High-Order Methods for Solving Monotone Variational Inequalities — arXiv:2609.23557

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23557
License (as archived)
CC0-1.0
Archived
2026-10-09T06:58:07.218Z
SHA-256 of the archived text
0bb90078c1fa4a07ead08e7af50ad251bd0f4d203d701974168ca8f6d6de985f
Stable URL of this page
https://metraipolis.com/documento/dc_179f43a1db4e

How to cite

Optimal High-Order Methods for Solving Monotone Variational Inequalities — arXiv:2609.23557 — arXiv (en), https://arxiv.org/abs/2609.23557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_179f43a1db4e (Metraipolis archive dc_179f43a1db4e, sha256 0bb90078c1fa4a07ead08e7af50ad251bd0f4d203d701974168ca8f6d6de985f)
BibTeX
@misc{dc179f43a1db4e,
  title = {Optimal High-Order Methods for Solving Monotone Variational Inequalities — arXiv:2609.23557},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23557},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_179f43a1db4e; sha256 0bb90078c1fa4a07ead08e7af50ad251bd0f4d203d701974168ca8f6d6de985f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) showed that a second-order method, NPE, converges at a rate of $\mathcal{O}(T^{-1.5})$. For convex-concave minimax optimization, a subclass of MVI problems, Chen, Liu, Luo, and Zhang (COLT 2025) recently improved this rate to $\tilde{\mathcal{O}}( T^{-1.75})$. However, the result has a substantial gap compared to the lower bound of $\Omega(T^{-2.5})$ established by Chen et al. (2026). In this paper, we propose a novel second-order method that achieves the optimal rate of $\mathcal{O}(T^{-2.5})$. Our algorithm also extends to higher-order methods: for any integer $ p \ge 1$, we obtain a $p$th-order method with a convergence rate of $\mathcal{O}(T^{-(3p-1)/2})$, matching the known lower bounds and therefore establishing optimal rates across all orders.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-22 in cs.GT).
Categorie arXiv: Optimization and Control (math.OC) ; Computer Science and Game Theory (cs.GT); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.23557 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:52:12.768Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).