arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.04091math.OC
收藏

二元逻辑斯谛回归确定性一阶方法的最坏情况数据集

Some Worst-Case Datasets of Deterministic First-Order Methods for Solving Binary Logistic Regression

Yuyuan Ouyang, Trevor Squires

摘要:

本文给出了求解大规模二元逻辑斯谛回归问题的确定性一阶方法的最坏情况数据集。在算法迭代次数远小于问题维数的假设下,对于我们的最差情况数据集,它至少需要$\mathcal{O}(1/\sqrt{\varepsilon})$一阶oracle查询来计算$\varepsilon$ -近似解。从传统的迭代复杂性分析的角度来看,二元逻辑斯谛回归损失函数与我们的最坏情况的数据集是新的最坏情况的函数类光滑凸优化问题的情况。

英文摘要:

We present in this paper some worst-case datasets of deterministic first-order methods for solving large-scale binary logistic regression problems. Under the assumption that the number of algorithm iterations is much smaller than the problem dimension, with our worst-case datasets it requires at least $\mathcal{O}(1/\sqrt{\varepsilon})$ first-order oracle inquiries to compute an $\varepsilon$-approximate solution. From traditional iteration complexity analysis point of view, the binary logistic regression loss functions with our worst-case datasets are new worst-case function instances among the class of smooth convex optimization problems.

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。

↑