A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method: Theory and Insights

Abstract

We derive a second-order ordinary differential equation (ODE), which is the limit of Nesterov’s accelerated gradient method. This ODE exhibits approximate equivalence to Nesterov’s scheme and thus can serve as a tool for analysis. We show that the continuous time ODE allows for a better understanding of Nesterov’s scheme. As a byproduct, we obtain a family of schemes with similar convergence rates. The ODE interpretation also suggests restarting Nesterov’s scheme leading to an algorithm, which can be rigorously proven to converge at a linear rate whenever the objective is strongly convex.

Cite

Text

Su et al. "A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method: Theory and Insights." Neural Information Processing Systems, 2014.

Markdown

[Su et al. "A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method: Theory and Insights." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/su2014neurips-differential/)

BibTeX

@inproceedings{su2014neurips-differential,
  title     = {{A Differential Equation for Modeling Nesterov’s Accelerated Gradient Method: Theory and Insights}},
  author    = {Su, Weijie and Boyd, Stephen and Candes, Emmanuel},
  booktitle = {Neural Information Processing Systems},
  year      = {2014},
  pages     = {2510-2518},
  url       = {https://mlanthology.org/neurips/2014/su2014neurips-differential/}
}