Metraipolis › archive › dc_4cf9200cd658

Halpern Iteration Achieves $\tilde{\mathcal{O}}(ε^{-1/p})$ $p$th-Order Oracle Complexity for Monotone Variational Inequalities — arXiv:2608.08463

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08463
License (as archived)
CC0-1.0
Archived
2026-10-19T09:05:25.259Z
SHA-256 of the archived text
72df0cd955fe9202f6812d7ed6830070c7cb43d4cc6ddd03e0ab4cc445ec4422
Stable URL of this page
https://metraipolis.com/documento/dc_4cf9200cd658

How to cite

Halpern Iteration Achieves $\tilde{\mathcal{O}}(ε^{-1/p})$ $p$th-Order Oracle Complexity for Monotone Variational Inequalities — arXiv:2608.08463 — arXiv (en), https://arxiv.org/abs/2608.08463 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4cf9200cd658 (Metraipolis archive dc_4cf9200cd658, sha256 72df0cd955fe9202f6812d7ed6830070c7cb43d4cc6ddd03e0ab4cc445ec4422)
BibTeX
@misc{dc4cf9200cd658,
  title = {Halpern Iteration Achieves $tildemathcalO(ε^-1/p)$ $p$th-Order Oracle Complexity for Monotone Variational Inequalities — arXiv:2608.08463},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08463},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4cf9200cd658; sha256 72df0cd955fe9202f6812d7ed6830070c7cb43d4cc6ddd03e0ab4cc445ec4422},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08463. 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 the rate of $\mathcal{O}(T^{-1.5})$. For convex-concave minimax optimization, a subset of MVI problems, Chen, Liu, Luo, and Zhang (COLT 2025) recently improved the complexity to $\tilde{\mathcal{O}}( T^{-1.75})$ . However, it is open whether the conjectured complexity for MVI can be improved. In this paper, by using a large-step inexact Halpern iteration, we propose a novel Halpern-NPE method that achieves an even faster rate of $\tilde{\mathcal{O}}(T^{-2})$ for solving MVIs. We also provide the $p$th-order generalization of our method. We first introduce an Anchored Tensor Method (ATM) that achieves the rate of $\mathcal{O}(T^{-(p-1)})$, and then combine it with the Halpern iteration to achieve a faster convergence rate of $\tilde{\mathcal{O}}(T^{-p})$. This improves all prior results for $p \ge 2$ and matches the classical extragradient method for $p=1$.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-11 in math.OC).
Categorie arXiv: Optimization and Control (math.OC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.08463 — 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 2026-10-19T09:03:32.057Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).