Iterative Linearized Control: Stable Algorithms and Complexity Guarantees

@InProceedings{pmlr-v97-roulet19a,
  title = 	 {Iterative Linearized Control: Stable Algorithms and Complexity Guarantees},
  author =       {Roulet, Vincent and Srinivasa, Siddhartha and Drusvyatskiy, Dmitriy and Harchaoui, Zaid},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {5518--5527},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/roulet19a/roulet19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/roulet19a.html},
  abstract = 	 {We examine popular gradient-based algorithms for nonlinear control in the light of the modern complexity analysis of first-order optimization algorithms. The examination reveals that the complexity bounds can be clearly stated in terms of calls to a computational oracle related to dynamic programming and implementable by gradient back-propagation using machine learning software libraries such as PyTorch or TensorFlow. Finally, we propose a regularized Gauss-Newton algorithm enjoying worst-case complexity bounds and improved convergence behavior in practice. The software library based on PyTorch is publicly available.}
}