# OCP-GN: A Scalable Second-order Optimizer for Stochastic Optimization

arXiv: https://arxiv.org/abs/2512.24552 · HTML: https://mlsanity.com/paper/2512.24552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 7 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Builds on (most cited first, 3 of 3)

- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [An Efficient Algorithm for Learning-Based Visual Localization](https://mlsanity.com/paper/2511.04232/) (2025)

## Abstract (arXiv)

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.