mlsanityData to 7 Oct 2026

Fast symplectic integrator for Nesterov-type acceleration method

arXiv 2106.07620 ↗First posted 1 Jun 2021math.NA cs.LG cs.NAcited by 1

Not on the map. Why?

Abstract (arXiv)

In this paper, explicit stable integrators based on symplectic and contact geometries are proposed for a non-autonomous ordinarily differential equation (ODE) found in improving convergence rate of Nesterov's accelerated gradient method. Symplectic geometry is known to be suitable for describing Hamiltonian mechanics, and contact geometry is known as an odd-dimensional counterpart of symplectic geometry. Moreover, a procedure, called symplectization, is a known way to construct a symplectic manifold from a contact manifold, yielding Hamiltonian systems from contact ones. It is found in this paper that a previously investigated non-autonomous ODE can be written as a contact Hamiltonian system. Then, by symplectization of a non-autonomous contact Hamiltonian vector field expressing the non-autonomous ODE, novel symplectic integrators are derived. Because the proposed symplectic integrators preserve hidden symplectic and contact structures in the ODE, they should be more stable than the Runge-Kutta method. Numerical experiments demonstrate that, as expected, the second-order symplectic integrator is stable and high convergence rates are achieved.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 49 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

17 of 49 references.

References · 17

  1. 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 203
  2. 2016A Variational Perspective on Accelerated Methods in Optimizationcited by 108
  3. 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
  4. 2019A Survey of Optimization Methods from a Machine Learning Perspectivecited by 90
  5. 2019Acceleration via Symplectic Discretization of High-Resolution Differential Equationscited by 27
  6. 2020On dissipative symplectic integration with applications to gradient-based optimizationcited by 23
  7. 2017Dissipativity Theory for Nesterov's Accelerated Methodcited by 22
  8. 2018Direct Runge-Kutta Discretization Achieves Accelerationcited by 21
  9. 2017Analysis of Optimization Algorithms via Integral Quadratic Constraints: Nonstrongly Convex Problemscited by 19
  10. 2016Regularized Nonlinear Accelerationcited by 18
  11. 2018Lyapunov Theory for Discrete Time Systemscited by 15
  12. 2019Generalized Momentum-Based Methods: A Hamiltonian Perspectivecited by 12
5 more
  1. 2020Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue Problemscited by 12
  2. 2017Rate of convergence of the Nesterov accelerated gradient method in the subcritical case α ≤ 3cited by 9
  3. 2019Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functionscited by 8
  4. 2018On the Curved Geometry of Accelerated Optimizationcited by 6
  5. 2019Bregman dynamics, contact transformations and convex optimizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.