Skip to yearly menu bar Skip to main content


A Dynamical Systems Perspective on Nesterov Acceleration

Michael Muehlebach · Michael Jordan

Pacific Ballroom #205

Keywords: [ Non-convex Optimization ] [ Large Scale Learning and Big Data ] [ Convex Optimization ]


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.

Live content is unavailable. Log in and register to view live content