Can I read Large-scale Randomized-coordinate Descent Methods with Non-separable Linear Constraints on EtoBox?

Large-scale Randomized-coordinate Descent Methods with Non-separable Linear Constraints by Reddi, Sashank; Hefny, Ahmed; Downey, Carlton; Dubey, Avinava; Sra, Suvrit is a scholarly article available to read on EtoBox.

What is Large-scale Randomized-coordinate Descent Methods with Non-separable Linear Constraints about?

We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable, but let them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making the global iteration complexity have an exponential dependence on the number of constraints. We present algorithms and analysis for four key problem scenarios: (i) smooth; (ii) smooth + nonsmooth separable; (iii) asynchronous parallel; and (iv) stochastic. We illustrate empirical behavior of our algorithms by simulation experiments.

Author

Reddi, Sashank; Hefny, Ahmed; Downey, Carlton; Dubey, Avinava; Sra, Suvrit

Published

2014

Language

EN