This work demonstrates the utility of gradients for the global optimization of certain differentiable functions with many suboptimal local minima. To this end, a principle for generating search directions from non-local quadratic approximants based on gradients of the objective function is analyzed. Experiments measure the quality of non-local search directions as well as the performance of a proposed simplistic algorithm, of the covariance matrix adaptation evolution strategy (CMA-ES), and of a randomly reinitialized Broyden-Fletcher-Goldfarb-Shanno (BFGS) method.

翻译：本文证明了梯度在具有大量次优局部极小值的特定可微函数全局优化中的实用性。为此，本文分析了一种基于目标函数梯度从非局部二次逼近生成搜索方向的原理。实验评估了非局部搜索方向的质量，以及所提出的简单算法、协方差矩阵自适应进化策略（CMA-ES）和随机重启的Broyden-Fletcher-Goldfarb-Shanno（BFGS）方法的性能。