ICML 2018oral16 citations

Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework

Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Tamas Keviczky

Abstract

Ordinary differential equations, and in general a dynamical system viewpoint, have seen a resurgence of interest in developing fast optimization methods, mainly thanks to the availability of well-established analysis tools. In this study, we pursue a similar objective and propose a class of hybrid control systems that adopts a 2nd-order differential equation as its continuous flow. A distinctive feature of the proposed differential equation in comparison with the existing literature is a state-dependent, time-invariant damping term that acts as a feedback control input. Given a user-defined scalar $\alpha$, it is shown that the proposed control input steers the state trajectories to the global optimizer of a desired objective function with a guaranteed rate of convergence $\mathcal{O}(e^{-\alpha t})$. Our framework requires that the objective function satisfies the so called Polyak–{Ł}ojasiewicz inequality. Furthermore, a discretization method is introduced such that the resulting discrete dynamical system possesses an exponential rate of convergence.

BibTeX
@InProceedings{pmlr-v80-kolarijani18a,
  title = 	 {Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework},
  author =       {Kolarijani, Arman Sharifi and Esfahani, Peyman Mohajerin and Keviczky, Tamas},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  pages = 	 {2728--2736},
  year = 	 {2018},
  editor = 	 {Dy, Jennifer and Krause, Andreas},
  volume = 	 {80},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {10--15 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v80/kolarijani18a/kolarijani18a.pdf},
  url = 	 {https://proceedings.mlr.press/v80/kolarijani18a.html},
  abstract = 	 {Ordinary differential equations, and in general a dynamical system viewpoint, have seen a resurgence of interest in developing fast optimization methods, mainly thanks to the availability of well-established analysis tools. In this study, we pursue a similar objective and propose a class of hybrid control systems that adopts a 2nd-order differential equation as its continuous flow. A distinctive feature of the proposed differential equation in comparison with the existing literature is a state-dependent, time-invariant damping term that acts as a feedback control input. Given a user-defined scalar $\alpha$, it is shown that the proposed control input steers the state trajectories to the global optimizer of a desired objective function with a guaranteed rate of convergence $\mathcal{O}(e^{-\alpha t})$. Our framework requires that the objective function satisfies the so called Polyak–{Ł}ojasiewicz inequality. Furthermore, a discretization method is introduced such that the resulting discrete dynamical system possesses an exponential rate of convergence.}
}
Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework · ICML 2018