一般矩阵函数的伴随微分
Adjoint Differentiation for generic matrix functions
摘要:
本文导出了$C=f(A)$形式的方阵运算的伴随$\overline{A}$的一个公式,其中$f$在每个特征值的邻域内是全纯的。然后,我们应用该公式推导出封闭形式的表达式,在特定情况下的利益,如情况下,当我们有一个频谱分解$A=UDU^{-1}$,频谱截止$C=A_+$和最近的相关矩阵例程。最后,我们解释了如何简化正则化线性回归系数的伴随计算。
英文摘要:
We derive a formula for the adjoint $\overline{A}$ of a square-matrix operation of the form $C=f(A)$, where $f$ is holomorphic in the neighborhood of each eigenvalue. We then apply the formula to derive closed-form expressions in particular cases of interest such as the case when we have a spectral decomposition $A=UDU^{-1}$, the spectrum cut-off $C=A_+$ and the Nearest Correlation Matrix routine. Finally, we explain how to simplify the computation of adjoints for regularized linear regression coefficients.
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。