Black-Box Optimization via Generative Adversarial Nets

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, bringing some unexpected obstacles to these methods. In this paper, we present a generative adversarial nets-based optimizer (OPT-GAN) to adapt to diverse black-box problems via estimating the distribution of optima. The method learns the extensive distribution of the optimal region dominated by selective and randomly moving candidates, balancing the exploration and exploitation. Experiments conducted on Black-box Optimization Benchmarking (BBOB) problems and several other benchmarks with diversified distributions exhibit that, the OPT-GAN outperforms many traditional and neural net-based BBO algorithms.