D-最优设计算法中非最优支撑点去除的改进
Improvements on removing non-optimal support points in D-optimum design algorithms
摘要:
我们改进了Pronzato [2003]中的不等式。D-最优设计算法中非最优支撑点的去除。中央集权主义者可能吧Lett. 63,223-228]以在搜索$D$最优设计期间从设计空间中移除点。设$ξ$是紧致空间$\mathcal{X} \subset \mathbb{R}^m$上具有非奇异信息矩阵的任意设计,$m+ε$是所有$\mathbf{x} \in \mathcal{X}$上方差函数$d(ξ,\mathbf{x})$的最大值.证明了$D$ -最优设计在$\mathcal{X}$上的任何支撑点$\mathbf{x}_{*}$必须满足不等式$d(ξ,\mathbf{x}_{*}) \geq m(1+ε/2-\sqrt{ε(4+ε-4/m)}/2)$ .我们表明,这个新的下限$d(ξ,\mathbf{x}_{*})$是,在某种意义上说,最好的可能,以及它如何可以用来加速算法的$D$ -最优设计。
英文摘要:
We improve the inequality used in Pronzato [2003. Removing non-optimal support points in D-optimum design algorithms. Statist. Probab. Lett. 63, 223-228] to remove points from the design space during the search for a $D$-optimum design. Let $ξ$ be any design on a compact space $\mathcal{X} \subset \mathbb{R}^m$ with a nonsingular information matrix, and let $m+ε$ be the maximum of the variance function $d(ξ,\mathbf{x})$ over all $\mathbf{x} \in \mathcal{X}$. We prove that any support point $\mathbf{x}_{*}$ of a $D$-optimum design on $\mathcal{X}$ must satisfy the inequality $d(ξ,\mathbf{x}_{*}) \geq m(1+ε/2-\sqrt{ε(4+ε-4/m)}/2)$. We show that this new lower bound on $d(ξ,\mathbf{x}_{*})$ is, in a sense, the best possible, and how it can be used to accelerate algorithms for $D$-optimum design.
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。