Skip to Main content Skip to Navigation
Book sections

Optimization in High Dimensions via Accelerated, Parallel and Proximal Coordinate Descent

Abstract : We propose a new randomized coordinate descent method for minimizing the sum of convex functions each of which depends on a small number of coordinates only. Our method (APPROX) is simultaneously Accelerated, Parallel and PROXimal; this is the first time such a method is proposed. In the special case when the number of processors is equal to the number of coordinates, the method converges at the rate $2\bar{\omega}\bar{L} R^2/(k+1)^2 $, where $k$ is the iteration counter, $\bar{\omega}$ is a data-weighted \emph{average} degree of separability of the loss function, $\bar{L}$ is the \emph{average} of Lipschitz constants associated with the coordinates and individual functions in the sum, and $R$ is the distance of the initial point from the minimizer. We show that the method can be implemented without the need to perform full-dimensional vector operations, which is the major bottleneck of accelerated coordinate descent, rendering it impractical. The fact that the method depends on the average degree of separability, and not on the maximum degree, can be attributed to the use of new safe large stepsizes, leading to improved expected separable overapproximation (ESO). These are of independent interest and can be utilized in all existing parallel randomized coordinate descent algorithms based on the concept of ESO. In special cases, our method recovers several classical and recent algorithms such as simple and accelerated proximal gradient descent, as well as serial, parallel and distributed versions of randomized block coordinate descent. \new{Due of this flexibility, APPROX had been used successfully by the authors in a graduate class setting as a modern introduction to deterministic and randomized proximal gradient methods. Our bounds match or improve on the best known bounds for each of the methods APPROX specializes to. Our method has applications in a number of areas, including machine learning, submodular optimization, linear and semidefinite programming.
Document type :
Book sections
Complete list of metadata
Contributor : TelecomParis HAL Connect in order to contact the contributor
Submitted on : Friday, September 13, 2019 - 4:53:59 PM
Last modification on : Wednesday, November 24, 2021 - 9:54:14 AM


  • HAL Id : hal-02287359, version 1


Olivier Fercoq, Peter Richtárik. Optimization in High Dimensions via Accelerated, Parallel and Proximal Coordinate Descent. SIAM Review, SIAM, 2016. ⟨hal-02287359⟩



Record views