Combinatorial Preconditioners for Proximal Algorithms on Graphs

01/16/2018
by   Thomas Möllenhoff, et al.
0

We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We prove that certain decompositions lead to a theoretically optimal condition number. We also show how ideal decompositions can be realized using matroid partitioning and propose efficient greedy variants thereof for large-scale problems. Coupled with specialized solvers for the resulting scaled proximal subproblems, the preconditioned algorithm achieves competitive performance in machine learning and vision applications.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset