Projects per year
Abstract
In this paper we consider the problem of minimizing a convex function using a randomized block coordinate descent method. One of the key steps at each iteration of the algorithm is determining the update to a block of variables. Existing algorithms assume that in order to compute the update, a particular subproblem is solved exactly. In his work we relax this requirement, and allow for the subproblem to be solved inexactly, leading to an inexact block coordinate descent method. Our approach incorporates the best known results for exact updates as a special case. Moreover, these theoretical guarantees are complemented by practical considerations: the use of iterative techniques to determine the update as well as the use of preconditioning for further acceleration.
Original language  English 

Publisher  ArXiv 
Publication status  Published  19 Apr 2013 
Keywords
 math.OC
 cs.AI
 stat.ML
Fingerprint
Dive into the research topics of 'Inexact Coordinate Descent: Complexity and Preconditioning'. Together they form a unique fingerprint.Projects
 1 Finished

Science and Innovation: Numerical Algorithms and Intelligent Software for the Evolving HPC Platform
1/08/09 → 31/07/14
Project: Research