ODE解的类别:光滑性、覆盖数、噪声函数拟合的含义和光滑现象的诅咒
Classes of ODE solutions: smoothness, covering numbers, implications for noisy function fitting, and the curse of smoothness phenomenon
摘要:
许多从数据中恢复常微分方程解的数值方法依赖于在最小二乘准则下使用基函数或核函数来近似解。这种方法的准确性取决于解决方案的平滑性。本文通过建立关于ODE解类的光滑性和覆盖数(作为其“大小”的度量)的新结果,为这些方法提供了理论基础。我们的结果提供了答案,“如何做的光滑程度和”的大小“一类常微分方程的影响”的大小相关联的类的解决方案?“我们证明:(1)对于$y^{'}=f\left(y\right)$和$y^{'}=f\left(x,\,y\right)$,如果所有$k$的绝对值若$f$的($k\leqβ+1$)阶导数被$1$限制,则解最终得到$(k+1)$阶导数,其幅值在$k$中快速增长--“光滑的诅咒”;(2)一元函数的$(β+2)-$度光滑解类的覆盖数的上界大于“标准”$(β+2)-$度光滑解类的上界;(3)当$n=Ω\left(\left(β\sqrt{\log\left(β\vee1\right)}\right)^{4β+10}\right)$时,最小二乘拟合的均方误差收敛速度不大于$\left(\frac{1}{n}\right)^{\frac{2\left(β+2\right)}{2\left(β+2\right)+1}}$,在此条件下,当$y^{'}=f\left(x,\,y\right)$时,收敛速度$\left(\frac{1}{n}\right)^{\frac{2\left(β+2\right)}{2\left(β+2\right)+1}}$是极小极大最优的;(4)更一般地,对于高阶Picard型常微分方程,$y^{\left(m\right)}=f\left(x,\,y,\,y^{'},\,...,y^{\left(m-1\right)}\right)$,解类的覆盖数由$f$所覆盖的类$\mathcal{F}$的覆盖数与初始值所在的集合的覆盖数的乘积从上限定。
英文摘要:
Many numerical methods for recovering ODE solutions from data rely on approximating the solutions using basis functions or kernel functions under a least square criterion. The accuracy of this approach hinges on the smoothness of the solutions. This paper provides a theoretical foundation for these methods by establishing novel results on the smoothness and covering numbers of ODE solution classes (as a measure of their "size"). Our results provide answers to "how do the degree of smoothness and the "size" of a class of ODEs affect the "size" of the associated class of solutions?" We show that: (1) for $y^{'}=f\left(y\right)$ and $y^{'}=f\left(x,\,y\right)$, if the absolute values of all $k$th ($k\leqβ+1$) order derivatives of $f$ are bounded by $1$, then the solution can end up with the $(k+1)$th derivative whose magnitude grows factorially fast in $k$ -- "a curse of smoothness"; (2) our upper bounds for the covering numbers of the $(β+2)-$degree smooth solution classes are greater than those of the "standard" $(β+2)-$degree smooth class of univariate functions; (3) the mean squared error of least squares fitting for noisy recovery has a convergence rate no larger than $\left(\frac{1}{n}\right)^{\frac{2\left(β+2\right)}{2\left(β+2\right)+1}}$ if $n=Ω\left(\left(β\sqrt{\log\left(β\vee1\right)}\right)^{4β+10}\right)$, and under this condition, the rate $\left(\frac{1}{n}\right)^{\frac{2\left(β+2\right)}{2\left(β+2\right)+1}}$ is minimax optimal in the case of $y^{'}=f\left(x,\,y\right)$; (4) more generally, for the higher order Picard type ODEs, $y^{\left(m\right)}=f\left(x,\,y,\,y^{'},\,...,y^{\left(m-1\right)}\right)$, the covering number of the solution class is bounded from above by the product of the covering number of the class $\mathcal{F}$ that $f$ ranges over and the covering number of the set where initial values lie.
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。