We study the average $\mbox{CV}_{loo}$ stability of kernel ridge-less regression and derive corresponding risk bounds. We show that the interpolating solution with minimum norm minimizes a bound on $\mbox{CV}_{loo}$ stability, which in turn is controlled by the condition number of the empirical kernel matrix. The latter can be characterized in the asymptotic regime where both the dimension and cardinality of the data go to infinity. Under the assumption of random kernel matrices, the corresponding test error should be expected to follow a double descent curve.

翻译：我们研究了内核无脊椎回归的稳定性平均值$mbox{CV ⁇ Loo},并得出了相应的风险界限。我们表明,具有最低规范的内插解决方案最大限度地减少了对美元(mbox{CV ⁇ Loo})稳定性的约束,而这反过来又受经验内核矩阵条件数的制约。后者可以在数据尺寸和基点都无穷无尽的无药可循制度中加以描述。根据随机内核矩阵的假设,相应的测试错误应该遵循双向曲线。