Work

Accelerated mirror descent in continuous and discrete time

Year: 2015
Type: article
Abstract: We study accelerated mirror descent dynamics in continuous and discrete time. Combining the original continuous-time motivation of mirror descent with a recent ODE interpretation of Nesterov's accelerated method, we propose a family of continuous-time descent dynamics for convex functions with Lipschitz gradients, such that the solution trajectories converge to the optimum at a O(1/t2) rate. We then show that a large family of first-order accelerated methods can be obtained as a discretization of the ODE, and these methods converge at a O(1/k2) rate. This connection between accelerated mirror descent and the ODE provides an intuitive approach to the design and analysis of accelerated first-order algorithms.
Language: English
Open Access status: green
OpenAlex ID: W2184596805
FWCI: 7.343
Cites: 32
Cited by: 201
Related to: 9