Revisiting Decomposable Submodular Function Minimization with Incidence Relations
This work addresses computational bottlenecks in optimization for machine learning applications, representing an incremental improvement.
The authors tackled decomposable submodular function minimization by exploiting incidence relations to improve solver convergence rates, developing new scalable projection and coordinate descent methods with rigorous convergence analysis.
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.