Metraipolis › archive › dc_655a8cf372aa
Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization — arXiv:2609.18728
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18728
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:40:21.898Z
- SHA-256 of the archived text
4dd19961128832618266f3c4fb02ead9e2e96889584d2b4bebab3085595c04c7- Stable URL of this page
https://metraipolis.com/documento/dc_655a8cf372aa
How to cite
Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization — arXiv:2609.18728 — arXiv (en), https://arxiv.org/abs/2609.18728 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_655a8cf372aa (Metraipolis archive dc_655a8cf372aa, sha256 4dd19961128832618266f3c4fb02ead9e2e96889584d2b4bebab3085595c04c7)
BibTeX
@misc{dc655a8cf372aa,
title = {Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization — arXiv:2609.18728},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18728},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_655a8cf372aa; sha256 4dd19961128832618266f3c4fb02ead9e2e96889584d2b4bebab3085595c04c7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18728. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study deterministic adaptive optimization of globally $\beta$-smooth, $\mu$-strongly convex functions using exact scalar function values. Queries and outputs lie in $B_2^d(R)$, and the minimizer lies in $B_2^d(R/2)$. Set $\kappa=\beta/\mu$, $Q=\beta R^2/\epsilon$, and $D_d=(d/\log(ed))^{1/3}$. For sufficiently large $d$ and $0<\epsilon\le c_\epsilon\beta R^2$, the minimax value complexity $N_\epsilon$ satisfies \[ \begin{aligned} N_\epsilon &\ge c d\min\{\sqrt Q,\sqrt\kappa,D_d\},\\ N_\epsilon &\le C d\min\left\{ \sqrt Q,\sqrt\kappa[1+\log_+(Q/\kappa)] \right\}, \end{aligned} \] where $c,C,c_\epsilon>0$ are universal constants and $\log_+(t)=\max\{0,\log t\}$. The lower bound uses an exactly shielded smooth chain and batched delayed rotations; the upper bound combines finite differences, acceleration, and restart. When $\min\{Q,\kappa\}\le D_d^2$, these bounds match up to constants in the accuracy-dominated regime $Q\le\kappa$ and at constant relative accuracy $\epsilon=\Theta(\mu R^2)$. For arbitrarily higher accuracy in the range $\kappa\le D_d^2$, the bounds differ by at most $1+\log(\mu R^2/\epsilon)$; the optimal accuracy dependence remains unresolved in general.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-17 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.18728 — 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 2026-10-15T15:08:22.602Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).