Metraipolis › archive › dc_bf614b490d27
Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities — arXiv:2609.15257
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15257
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:15:46.926Z
- SHA-256 of the archived text
a9f4e048e70a9721a4aef276b9a7cdd857d4d9382e688ec4d3fb4b44f795ad9c- Stable URL of this page
https://metraipolis.com/documento/dc_bf614b490d27
How to cite
Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities — arXiv:2609.15257 — arXiv (en), https://arxiv.org/abs/2609.15257 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf614b490d27 (Metraipolis archive dc_bf614b490d27, sha256 a9f4e048e70a9721a4aef276b9a7cdd857d4d9382e688ec4d3fb4b44f795ad9c)
BibTeX
@misc{dcbf614b490d27,
title = {Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities — arXiv:2609.15257},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15257},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf614b490d27; sha256 a9f4e048e70a9721a4aef276b9a7cdd857d4d9382e688ec4d3fb4b44f795ad9c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15257. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We analyze a stochastic algorithm with Halpern-type anchoring for constrained convex-concave problems and monotone variational inequalities. This single-loop and single-call algorithm uses one unbiased sample of the gradient operator at every iteration, to be applicable to monotone games with noisy feedback. With $t$ denoting the iteration counter, we prove an anytime last-iterate convergence rate of $O(t^{-1/4})$ for both the gradient-mapping norm and restricted gap, bypassing the $O(t^{-1/5})$ constrained-anytime bottleneck in the literature. Specializing then to multi-point oracles, we use variance reduction to achieve the $O(t^{-1/2})$ rate with an anytime single-loop algorithm using $2$ samples per iteration. Our results allow constrained problems with a potentially unbounded feasible set; as well as a structured class of stochastic oracles whose variance need not be uniformly bounded.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15257 — 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 2026-10-15T23:54:14.956Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).