循环子空间回归的一种快速算法及其在定量构效关系中的应用

循环子空间回归（ＣＳＲ）通过改变解空间的维数，可以获取一系列的回归模型，其中包括最小二乘回归（ＬＳＲ）、主成分回归（ＰＣＲ）、偏最小二乘回归（ＰＬＳＲ）和许多中间回归，从中可挑选最优回归模型。本文将分析ＣＳＲ的原理，给出一种可行的快速的ＣＳＲ算法（ＲＣＳＲ），以提高计算速率和精度，并将其成功地应用于苯乙酰胺类除草剂定量构效关系的建模。

A Rapid Algorithm of Cyclic Subspace Regression and Its Application to Quantitative Structure-Activity Relationships

By changing the dimension of solution space, cyclic subspace regression (CSR) gets a serial of regression models which contains least square regression, principal component regression, partial least square regression and other medial regression outcomes. Then the optimal model can be picked out according to a certain criterion. This paper analyzes cyclic subspace regression, and gives a rapid algorithm of cyclic subspace regression (RCSR) to reduce the calculation. It has been successfully applied to the quantitative structure - activity relationship simulation of pesticides.