Research
OCP-GN: A Scalable Second-order Optimizer for Stochastic Optimization
arXiv:2512.24552v2 Announce Type: replace Abstract: This paper proposes a novel second-order optimization algorithm based on the Optimal Control Principle (OCP), applicable to large-scale optimization
arXiv:2512.24552v2 Announce Type: replace Abstract: This paper proposes a novel second-order optimization algorithm based on the Optimal Control Principle (OCP), applicable to large-scale optimization problems in neural network training. The algorithm has a computational complexity of O(d) and strong robustness. Extensive experiments on multiple benchmarks demonstrate the significant superiority of the proposed method.
Source: arXiv cs.CV | 2026-05-12