自适应正则化优化方法慢收敛的例子并非孤立现象
Examples of slow convergence for adaptive regularization optimization methods are not isolated
AI总结:
本文重新审视无约束非凸优化的自适应正则化算法的慢收敛现象,证明该现象并非孤立,而是发生在一组非零测度的单变量函数上。
摘要:
在标准假设下,无约束非凸优化的自适应正则化算法被证明最多需要目标函数及其一阶、二阶导数的O(ε^{3/(3-q)})次求值,即可产生阶数q∈{1,2}的ε近似临界点。该界限对q∈{1,2}被证明是紧的。本文重新审视这些结果,并表明展现慢收敛的例子并非孤立的,该行为发生在一组非零测度的单变量函数上。
英文摘要:
The adaptive regularization algorithm for unconstrained nonconvex optimization was shown in Nesterov and Polyak (2006) and Cartis, Gould and Toint (2011) to require, under standard assumptions, at most $\mathcal{O}(ε^{3/(3-q)})$ evaluations of the objective function and its derivatives of degrees one and two to produce an $ε$-approximate critical point of order $q\in\{1,2\}$. This bound was shown to be sharp for $q \in\{1,2\}$. This note revisits these results and shows that the example for which slow convergence is exhibited is not isolated, but that this behaviour occurs for a subset of univariate functions of nonzero measure.
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。