Large-scale randomized-coordinate descent methods with non-separable linear constraints

UAI'15 Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, (2014)

Cited by: 19|Views61
EI

Abstract:

We develop randomized block coordinate descent (CD) methods for linearly constrained convex optimization. Unlike other large-scale CD methods, we do not assume the constraints to be separable, but allow them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making the globa...More

Code:

Data:

ZH
Your rating :
0

 

Tags
Comments