Metraipolis › archive › dc_e45cdeef526b
Tight Lower Bounds for Stochastic Nonconvex-Strongly-Concave Minimax Optimization — arXiv:2609.35206
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35206
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:06:47.829Z
- SHA-256 of the archived text
ff010cdde020b6ba87f496ba8022143cb5e1e27e96945e271ae0fec938a741df- Stable URL of this page
https://metraipolis.com/documento/dc_e45cdeef526b
How to cite
Tight Lower Bounds for Stochastic Nonconvex-Strongly-Concave Minimax Optimization — arXiv:2609.35206 — arXiv (en), https://arxiv.org/abs/2609.35206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e45cdeef526b (Metraipolis archive dc_e45cdeef526b, sha256 ff010cdde020b6ba87f496ba8022143cb5e1e27e96945e271ae0fec938a741df)
BibTeX
@misc{dce45cdeef526b,
title = {Tight Lower Bounds for Stochastic Nonconvex-Strongly-Concave Minimax Optimization — arXiv:2609.35206},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35206},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e45cdeef526b; sha256 ff010cdde020b6ba87f496ba8022143cb5e1e27e96945e271ae0fec938a741df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the stochastic first-order oracle complexity of finding $\epsilon$-stationary points of the primal function in smooth nonconvex-strongly-concave minimax optimization. For sufficiently small $\epsilon$, we establish lower bounds of $\Omega(\kappa L\Delta\sigma^2\epsilon^{-4})$ under the bounded-variance assumption and $\Omega(\kappa^{3/2}\bar L\Delta\sigma\epsilon^{-3})$ under the additional assumption of averaged smoothness. Here, $L$ and $\bar L$ denote the smoothness and averaged-smoothness constants, respectively, $\Delta$ is the initial primal gap, $\sigma^2$ bounds the oracle variance, and $\kappa=L/\mu$ or $\bar L/\mu$ in the respective settings, where $\mu$ is the strong-concavity parameter. Our bounded-variance lower bound improves the dependence on the condition number from $\kappa^{1/3}$ in previous lower bounds to $\kappa$, while our averaged-smoothness lower bound is the first of its kind. In both settings, the resulting lower bounds match existing upper bounds in their dependence on $\kappa$ and $\epsilon$. Our proofs are based on a unified quadratic lifting construction that transfers a hardness instance for stochastic nonconvex minimization to unconstrained minimax optimization while preserving the required variance and smoothness properties.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-29 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.35206 — 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 2026-10-07T22:42:39.275Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).