📄 中文摘要
提出了一种双时间尺度的神经动态双重方法，以解决分布鲁棒的几何联合机会约束优化问题。行向量的概率分布未知，属于某个分布不确定性集合。研究了三种不确定性集合以应对未知分布。神经动态双重方法基于三条投影方程设计。主要贡献在于提出了一种基于神经网络的方法，能够在不使用标准最先进求解方法的情况下，以概率收敛到全局最优解。研究表明，神经网络可以有效用于解决分布鲁棒的联合机会约束优化问题。
分布鲁棒几何联合机会约束优化：神经动态方法
📄 English Summary
Distributionally Robust Geometric Joint Chance-Constrained Optimization: Neurodynamic Approaches
A two-time scale neurodynamic duplex approach is proposed to solve distributionally robust geometric joint chance-constrained optimization problems. The probability distributions of the row vectors are unknown and belong to a certain distributional uncertainty set. Three uncertainty sets for the unknown distributions are studied. The neurodynamic duplex is designed based on three projection equations. The main contribution is a neural network-based method that converges in probability to the global optimum without relying on standard state-of-the-art solving methods. The research demonstrates that neural networks can be effectively utilized to address distributionally robust joint chance-constrained optimization problems.