论文标题
明确的梯度学习
Explicit Gradient Learning
论文作者
论文摘要
黑盒优化（BBO）方法可以找到与没有分析表示的复杂环境相互作用的系统的最佳策略。因此，它们在许多人工智能（AI）领域中引起了人们的关注。然而，经典的BBO方法在高维非凸问题中缺乏。因此，在现实世界中的AI任务中，它们经常被忽略。在这里，我们提出了一种BBO方法，称为显式梯度学习（EGL），旨在优化高维差的功能。我们通过在使用参数神经网络（NN）模型的方法中找到拟合目标函数的方法来得出EGL，并通过计算参数梯度来获得梯度信号。 EGL不符合该功能，而是训练ANN以直接估计客观梯度。我们证明了EGL在凸优化中的收敛性及其在优化的集成函数中的鲁棒性。我们评估EGL并实现最先进的结果，涉及两个具有挑战性的问题：（1）可可测试套件针对各种标准BBO方法； （2）在高维非凸图像生成任务中。
Black-Box Optimization (BBO) methods can find optimal policies for systems that interact with complex environments with no analytical representation. As such, they are of interest in many Artificial Intelligence (AI) domains. Yet classical BBO methods fall short in high-dimensional non-convex problems. They are thus often overlooked in real-world AI tasks. Here we present a BBO method, termed Explicit Gradient Learning (EGL), that is designed to optimize high-dimensional ill-behaved functions. We derive EGL by finding weak-spots in methods that fit the objective function with a parametric Neural Network (NN) model and obtain the gradient signal by calculating the parametric gradient. Instead of fitting the function, EGL trains a NN to estimate the objective gradient directly. We prove the convergence of EGL in convex optimization and its robustness in the optimization of integrable functions. We evaluate EGL and achieve state-of-the-art results in two challenging problems: (1) the COCO test suite against an assortment of standard BBO methods; and (2) in a high-dimensional non-convex image generation task.
