资源分类
》 资源 》论文》Revisiting Decomposable Submodular Function Minimization with Incidence Relations

Revisiting Decomposable Submodular Function Minimization with Incidence Relations

2020-02-17 | |  58 |   59 |   0

Abstract 

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.

上一篇：Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons

下一篇：Modular Networks: Learning to Decompose Neural Computation

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...