Black Box Algorithm Selection by Convolutional Neural Network
This work addresses the algorithm selection challenge for researchers and practitioners in optimization, though it is incremental as it applies existing CNN architectures to a new data representation.
The paper tackled the problem of selecting the best optimization algorithm for black-box optimization problems by using a convolutional neural network (CNN) to classify algorithms based on 2-D images of problem landscapes, achieving effective results on BBOB functions.
Although a large number of optimization algorithms have been proposed for black box optimization problems, the no free lunch theorems inform us that no algorithm can beat others on all types of problems. Different types of optimization problems need different optimization algorithms. To deal with this issue, researchers propose algorithm selection to suggest the best optimization algorithm from the algorithm set for a given unknown optimization problem. Usually, algorithm selection is treated as a classification or regression task. Deep learning, which has been shown to perform well on various classification and regression tasks, is applied to the algorithm selection problem in this paper. Our deep learning architecture is based on convolutional neural network and follows the main architecture of visual geometry group. This architecture has been applied to many different types of 2-D data. Moreover, we also propose a novel method to extract landscape information from the optimization problems and save the information as 2-D images. In the experimental section, we conduct three experiments to investigate the classification and optimization capability of our approach on the BBOB functions. The results indicate that our new approach can effectively solve the algorithm selection problem.