Machine learning sklearn:SVR无法推广加法器函数

这是我学习加法器函数的SVR（y=x1+x2）：

但结果并不是预期的：

Input values are those in the train data:
1 + 2 = 6.007171

Input values are those in the train data:
5 + 6 = 9.595818

Input values are those NOT in the train data, but in range:
5 + 5 = 8.533934

Input values are those NOT in the train data, and OUT of range:
9 + 1 = 9.170507

---

sklearn SVR是否可以推广加法器函数？要让SVR学习x1+x2，上面的代码中应该做什么更改？

三次多项式核的方差太大，无法正确预测如此简单的函数，尤其是在如此小的数据集上。这是基于偏差/方差权衡。在这种情况下，您的模型失去了方差，而几乎没有任何偏差（您的函数过于复杂）。甚至低阶多项式和径向基函数也是如此

降低模型的方差就可以做到这一点。只需使用线性核

Model=svm.SVR（kernel=“linear”）

线性核支持向量机的结果如下：

Input values are those in the train data:
1 + 2 = 3.100000

Input values are those in the train data:
5 + 6 = 10.966667

Input values are those NOT in the train data, but in range:
5 + 5 = 9.983333

Input values are those NOT in the train data, and OUT of range:
9 + 1 = 9.983333

Input values are those in the train data:
1 + 2 = 3.100000

Input values are those in the train data:
5 + 6 = 10.966667

Input values are those NOT in the train data, but in range:
5 + 5 = 9.983333

Input values are those NOT in the train data, and OUT of range:
9 + 1 = 9.983333