A Dynamical Systems Perspective on Nesterov Acceleration

05/17/2019
by   Michael Muehlebach, et al.
4

We present a dynamical system framework for understanding Nesterov's accelerated gradient method. In contrast to earlier work, our derivation does not rely on a vanishing step size argument. We show that Nesterov acceleration arises from discretizing an ordinary differential equation with a semi-implicit Euler integration scheme. We analyze both the underlying differential equation as well as the discretization to obtain insights into the phenomenon of acceleration. The analysis suggests that a curvature-dependent damping term lies at the heart of the phenomenon. We further establish connections between the discretized and the continuous-time dynamics.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/23/2021

Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization

Viewing optimization methods as numerical integrators for ordinary diffe...
research
03/04/2015

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

We derive a second-order ordinary differential equation (ODE) which is t...
research
02/11/2021

A Continuized View on Nesterov Acceleration

We introduce the "continuized" Nesterov acceleration, a close variant of...
research
11/12/2019

Shadowing Properties of Optimization Algorithms

Ordinary differential equation (ODE) models of gradient-based optimizati...
research
06/10/2021

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip

We introduce the continuized Nesterov acceleration, a close variant of N...
research
12/09/2021

A More Stable Accelerated Gradient Method Inspired by Continuous-Time Perspective

Nesterov's accelerated gradient method (NAG) is widely used in problems ...
research
03/29/2023

Ordinary Differential Equation-based Sparse Signal Recovery

This study investigates the use of continuous-time dynamical systems for...

Please sign up or login with your details

Forgot password? Click here to reset