Poster
Revisiting Decomposable Submodular Function Minimization with Incidence Relations
Pan Li · Olgica Milenkovic
Room 210 #39
Keywords: [ Submodular Optimization ] [ Convex Optimization ] [ Combinatorial Optimization ]
We introduce a new approach to decomposable submodular function minimization (DSFM) that exploits incidence relations. Incidence relations describe which variables effectively influence the component functions, and when properly utilized, they allow for improving the convergence rates of DSFM solvers. Our main results include the precise parametrization of the DSFM problem based on incidence relations, the development of new scalable alternative projections and parallel coordinate descent methods and an accompanying rigorous analysis of their convergence rates.
Live content is unavailable. Log in and register to view live content