# DDPNOpt: Differential Dynamic Programming Neural Optimizer

arXiv: https://arxiv.org/abs/2002.08809 · HTML: https://mlsanity.com/paper/2002.08809/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 4 of 4)

- [Towards Robust Neural Networks via Close-loop Control](https://mlsanity.com/paper/2102.01862/) (2021)
- [PID Control-Based Self-Healing to Improve the Robustness of Large Language Models](https://mlsanity.com/paper/2404.00828/) (2024)
- [Dynamic Game Theoretic Neural Optimizer](https://mlsanity.com/paper/2105.03788/) (2021)
- [Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective](https://mlsanity.com/paper/2311.10223/) (2023)

## Abstract (arXiv)

Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorithmic development remains relatively limited. In this work, we make an attempt along this line by reformulating the training procedure from the trajectory optimization perspective. We first show that most widely-used algorithms for training DNNs can be linked to the Differential Dynamic Programming (DDP), a celebrated second-order method rooted in the Approximate Dynamic Programming. In this vein, we propose a new class of optimizer, DDP Neural Optimizer (DDPNOpt), for training feedforward and convolution networks. DDPNOpt features layer-wise feedback policies which improve convergence and reduce sensitivity to hyper-parameter over existing methods. It outperforms other optimal-control inspired training methods in both convergence and complexity, and is competitive against state-of-the-art first and second order methods. We also observe DDPNOpt has surprising benefit in preventing gradient vanishing. Our work opens up new avenues for principled algorithmic design built upon the optimal control theory.