迭代算法终止准则

تم الإنشاء في: ١٨ يناير ٢٠٢٥

تمت الإجابة باستخدام OpenAI 01 بواسطة OpenAI01

سؤال

迭代算法中,xk+1-xk/xk<0.01叫什么

الفكرة

Clarifying iterative condition

The user asks about a condition in iterative methods where (xk+1xk)/xk<0.01(x_{k+1} - x_k)/ x_k < 0.01, likely referring to a relative error or convergence criterion.

Pinpointing a term

I’m thinking through various terms like "relative difference," "relative error," or "terminating condition" to describe the iterative algorithm's convergence criterion.

Thought about 迭代算法收敛条件,持续 6 秒

الإجابة

在数值迭代方法中,xk+1xkxk<0.01\dfrac{x_{k+1} - x_k}{x_k} < 0.01 这一形式通常被称为“相对误差小于 1%”或“相对变化量(relative difference)小于 1%”的终止判据/收敛准则。

  • 绝对误差判据一般指 xk+1xk<ε\bigl|x_{k+1} - x_k\bigr| < \varepsilon
  • 相对误差判据指 xk+1xkxk<ε\dfrac{\bigl|x_{k+1} - x_k\bigr|}{\lvert x_k\rvert} < \varepsilon

这里的 0.01 就是设定的允许误差(公差),即相对误差小于 1%。当迭代过程中满足此条件时,我们通常就可以认为算法已经达到所需的精度而停止。

مشاركة هذا السؤال والجواب