隐函数的高效自动微分
Efficient Automatic Differentiation of Implicit Functions
摘要:
基于导数的算法在统计学、机器学习和应用数学中无处不在。自动微分提供了一种算法方法,可以有效地从执行相关函数的计算机程序中评估这些导数。然而,为包含隐函数的程序实现自动微分,例如代数或微分方程的解,需要特别小心。当代的应用程序通常呼吁要么应用隐函数定理,或在某些情况下,专门的伴随方法。在本文中,我们表明,这两种方法可以推广到任何隐函数,虽然广义伴随方法通常是更有效的自动微分。为了展示这两种方法的相对优势和局限性,我们展示了它们在一套常见的隐函数上的应用。
英文摘要:
Derivative-based algorithms are ubiquitous in statistics, machine learning, and applied mathematics. Automatic differentiation offers an algorithmic way to efficiently evaluate these derivatives from computer programs that execute relevant functions. Implementing automatic differentiation for programs that incorporate implicit functions, such as the solution to an algebraic or differential equation, however, requires particular care. Contemporary applications typically appeal to either the application of the implicit function theorem or, in certain circumstances, specialized adjoint methods. In this paper we show that both of these approaches can be generalized to any implicit function, although the generalized adjoint method is typically more effective for automatic differentiation. To showcase the relative advantages and limitations of the two methods we demonstrate their application on a suite of common implicit functions.
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。