Abstract
One of the key steps at each iteration of a randomized block coordinate descent method consists in 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 this 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 and the use of preconditioning for further acceleration.
Original language | English (US) |
---|---|
Pages (from-to) | 144-176 |
Number of pages | 33 |
Journal | Journal of Optimization Theory and Applications |
Volume | 170 |
Issue number | 1 |
DOIs | |
State | Published - Jul 1 2016 |
Externally published | Yes |
ASJC Scopus subject areas
- Control and Optimization
- Management Science and Operations Research
- Applied Mathematics