AI 中文总结
该研究通过仅使用精确函数值,提出了凸优化问题中 oracle 复杂度的近二次下界,并扩展至混合整数优化场景。
AI 中文摘要
我们研究了在仅使用精确函数值的情况下,对欧几里得球面上的凸 Lipschitz 函数进行最小化所确定的查询复杂度。在精度为Θ(d^{-1/2})时,之前适用的下界为Ω(d),继承自更强的全一阶 oracle。而 Protasov 的仅值方法提供的上界需要 O(d²log²d) 次评估。通过在此设定中提供一个下界为Ω(d²/log(d+1)) 的 oracle 复杂度,我们因此弥合了自 1996 年以来的这一差距,直至多对数因子。此外,我们能够将这一结果提升到混合整数设置:使用函数值进行混合整数凸优化,其中包含 d 个连续变量和 n 个离散变量,需要 Ω(d²·2ⁿ) 次查询。
英文摘要
We study the deterministic query complexity of minimizing a convex Lipschitz function over a $d$-dimensional Euclidean ball using only exact function values. At accuracy $Θ(d^{-1/2})$, the previously applicable lower bound was $Ω(d)$, inherited from the stronger full first-order oracle, while an upper bound from Protasov's value-only method requires $O(d^2\log^2 d)$ evaluations. By providing a lower bound of $Ω(\,\frac{d^2}{\log(d+1)})$ on the oracle complexity in this setting, we thereby close this gap dating back to 1996, up to polylogarithmic factors. Furthermore, we are able to lift this result to the mixed-integer setting: Mixed-integer convex optimization with $d$ continuous and $n$ discrete variables using function values requires $\tildeΩ(d^2\cdot 2^n)$ queries.
Comments36 pages, 0 figures