Convergence analysis of kernel conjugate gradient for functional linear regression
Convergence analysis of kernel conjugate gradient for functional linear regression
复制标题
DOI：
10.30970/ana.2023.1.33
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Naveen Gupta;And S. SIVANANTHAN;Bharath K. Sriperumbudur
中科院分区：
文献类型：
--
作者：
Naveen Gupta;And S. SIVANANTHAN;Bharath K. Sriperumbudur
在再生核Hilbert空间框架下，利用正则化中的早期停止结果，讨论了泛函线性模型的共轭梯度算法的收敛性分析.我们建立了依赖于斜率函数的正则性条件和协方差算子与核算子的组合的特征值的衰减率的收敛速度。我们的收敛速度匹配的极大极小率从文献中。
In this paper, we discuss the convergence analysis of the conjugate gradient-based algorithm for the functional linear model in the reproducing kernel Hilbert space framework, utilizing early stopping results in regularization against over-fitting. We establish the convergence rates depending on the regularity condition of the slope function and the decay rate of the eigenvalues of the operator composition of covariance and kernel operator. Our convergence rates match the minimax rate available from the literature.