OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution
This work addresses the problem of efficiently finding global optima in black-box optimization for researchers and practitioners dealing with complex, real-world problems where analytical details are missing.
This paper introduces OPT-GAN, a generative adversarial network-based optimizer for black-box problems that learns the distribution of the optimum. It aims to overcome limitations of classical methods that rely on fixed a priori assumptions like Gaussianity, demonstrating superior performance on diverse black-box optimization benchmarks and high-dimensional real-world applications.
Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies to balance exploration-exploitation trade-off. It has potential to better adapt to the regularity and structure of diversified landscapes than other methods with fixed prior, e.g., Gaussian assumption or separability. Experiments on diverse BBO benchmarks and high dimensional real world applications exhibit that OPT-GAN outperforms other traditional and neural net-based BBO algorithms.