Analysis of the Gradient Method with an Armijo-Wolfe Line Search on a Class of Nonsmooth Convex Functions
For optimization researchers, it reveals unexpected failure modes of gradient methods with standard line searches on nonsmooth problems, challenging conventional understanding.
The paper analyzes the gradient method with Armijo-Wolfe line search on a class of nonsmooth convex functions, showing that for certain parameters the iterates converge to a non-optimal point despite the function being unbounded below, and provides conditions for divergence to -∞.
It has long been known that the gradient (steepest descent) method may fail on nonsmooth problems, but the examples that have appeared in the literature are either devised specifically to defeat a gradient or subgradient method with an exact line search or are unstable with respect to perturbation of the initial point. We give an analysis of the gradient method with steplengths satisfying the Armijo and Wolfe inexact line search conditions on the nonsmooth convex function $f(x) = a|x^{(1)}| + \sum_{i=2}^{n} x^{(i)}$. We show that if $a$ is sufficiently large, satisfying a condition that depends only on the Armijo parameter, then, when the method is initiated at any point $x_0 \in \R^n$ with $x^{(1)}_0\not = 0$, the iterates converge to a point $\bar x$ with $\bar x^{(1)}=0$, although $f$ is unbounded below. We also give conditions under which the iterates $f(x_k)\to-\infty$, using a specific Armijo-Wolfe bracketing line search. Our experimental results demonstrate that our analysis is reasonably tight.