Skip to yearly menu bar Skip to main content


Poster

Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization

Ahmet Alacaoglu · Quoc Tran Dinh · Olivier Fercoq · Volkan Cevher

Pacific Ballroom #171

Keywords: [ Convex Optimization ] [ Stochastic Methods ]


Abstract:

We propose a new randomized coordinate descent method for a convex optimization template with broad applications. Our analysis relies on a novel combination of four ideas applied to the primal-dual gap function: smoothing, acceleration, homotopy, and coordinate descent with non-uniform sampling. As a result, our method features the first convergence rate guarantees among the coordinate descent methods, that are the best-known under a variety of common structure assumptions on the template. We provide numerical evidence to support the theoretical results with a comparison to state-of-the-art algorithms.

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