This paper proposes a novel second-order optimization algorithm. It aims to address large-scale optimization problems in deep learning because it incorporates the OCP method and appropriately approximating the diagonal elements of the Hessian matrix. Extensive experiments on multiple standard visual localization benchmarks demonstrate the significant superiority of the proposed method. Compared with conventional optimiza tion algorithms, our framework achieves competitive localization accuracy while exhibiting faster convergence, enhanced training stability, and improved robustness to noise interference.

翻译：本文提出了一种新颖的二阶优化算法。该算法旨在解决深度学习中的大规模优化问题，因为它融合了OCP方法并适当近似了Hessian矩阵的对角元素。在多个标准视觉定位基准上进行的大量实验表明，所提方法具有显著优越性。与传统优化算法相比，我们的框架在实现具有竞争力的定位精度的同时，展现出更快的收敛速度、更强的训练稳定性以及对噪声干扰更好的鲁棒性。