arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.07239cs.LGmath.OC
收藏

随机优化中整数变量的样本复杂度

Sample Complexity of Stochastic Optimization with Integer Variables

Dept. of Applied Mathematics & Statistics(应用数学与统计学系);Johns Hopkins University(约翰霍普金斯大学);Microsoft Research (Redmond)(微软研究院(红mond));Dept. of Computer Science, PUC-Rio(计算机科学系,巴西圣保罗大学)

Hongyu Cheng, Yinghao Zheng, Marco Molinaro, Amitabh Basu

AI总结:

本文研究了随机优化中整数变量的样本复杂度,发现整数优化在某些情况下可能需要更多或更少的样本,取决于目标函数和约束的结构。

摘要:

我们建立了随机优化在整数域上的样本复杂度结果,特别是为了理解其与相应连续优化问题的复杂性。我们证明整数优化有时需要严格更多的样本,有时需要严格更少的样本,这取决于目标函数和约束的结构。1. 对于在ℓ∞球面子集上的Lipschitz目标函数,一般随机混合整数、非线性、非凸优化的统计复杂度与具有仅边界约束的随机线性优化相同。2. 对于在ℓ2球面子集上的Lipschitz目标函数,我们证明在某些情况下,整数优化所需的样本量可能比连续设置更小。为此,我们还建立了非凸连续随机优化的紧样本复杂度结果,这些结果在现有文献中尚未出现。3. 对于强凸、光滑的目标函数,整数优化的统计复杂度高于连续设置。特别是,我们证明整数优化需要Ω(1/ε²)的样本量来报告一个ε-近似解,而连续优化文献中已知的样本复杂度为O(1/ε)。

英文摘要:

We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect to the corresponding continuous optimization problem. We show that integer optimization can sometimes require strictly more samples and sometimes strictly smaller number of samples, depending on the structure of the objective and constraints. 1. For Lipschitz objectives over subsets of the $\ell_\infty$ ball, the statistical complexity of general stochastic mixed-integer, nonlinear, nonconvex optimization is exactly the same as stochastic linear optimization with just bound constraints. 2. For Lipschitz objectives over subsets of the $\ell_2$ ball, we show that integer optimization can require strictly *smaller* sample size compared to the continuous setting in a certain regime. To get to this result, we also establish tight sample complexity results for nonconvex continuous stochastic optimization which, to the best of our knowledge, do not appear in prior work. 3. For strongly convex, smooth objectives, integer optimization has high statistical complexity compared to the continuous setting. In particular, we show that integer optimization requires $Ω(1/ε^2)$ samples to report an $ε$-approximate solution, compared to the well-known $O(1/ε)$ sample complexity from the continuous optimization literature.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑