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 0912.1547math.OC
收藏

单位超立方体上函数变量间相互作用的度量

Measuring the interactions among variables of functions over the unit hypercube

Jean-Luc Marichal, Pierre Mathonet

摘要:

通过考虑一个给定的平方可积〔的〕函数$f\colon[0,1]^n\to\R$的最小二乘逼近的多线性多项式的一个指定的程度,我们定义了一个指数,衡量整体之间的相互作用变量的$f$。该定义推广了合作对策理论中引入的Banzhaf互动指数的概念。我们的方法部分灵感来自于多元线性回归分析,其中考虑了自变量之间的相互作用。我们表明,这种相互作用指数具有吸引力的性质,自然推广的Banzhaf相互作用指数的属性。特别地,我们将该指数解释为$f$的差导数的期望值,或者在$f$的某些自然条件下,解释为$f$的导数的期望值。这些解释显示了引入的相互作用指数与Grabisch和Labreuche定义的总体重要性指数之间的强烈相似性[7]。最后,我们讨论了一些应用的相互作用指数。

英文摘要:

By considering a least squares approximation of a given square integrable function $f\colon[0,1]^n\to\R$ by a multilinear polynomial of a specified degree, we define an index which measures the overall interaction among variables of $f$. This definition extends the concept of Banzhaf interaction index introduced in cooperative game theory. Our approach is partly inspired from multilinear regression analysis, where interactions among the independent variables are taken into consideration. We show that this interaction index has appealing properties which naturally generalize the properties of the Banzhaf interaction index. In particular, we interpret this index as an expected value of the difference quotients of $f$ or, under certain natural conditions on $f$, as an expected value of the derivatives of $f$. These interpretations show a strong analogy between the introduced interaction index and the overall importance index defined by Grabisch and Labreuche [7]. Finally, we discuss a few applications of the interaction index.

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。

↑