资源分类
》 资源 》论文》Universality of the Local Marginal Polytope

Universality of the Local Marginal Polytope

2019-11-28 | |  57 |   43 |   0

Abstract We show that solving the LP relaxation of the MAP inference problem in graphical models (also known as the minsum problem, energy minimization, or weighted constraint satisfaction) is not easier than solving any LP. More precisely, any polytope is linear-time representable by a local marginal polytope and any LP can be reduced in linear time to a linear optimization (allowing infifinite weights) over a local marginal polytope.

上一篇：Leveraging Structure from Motion to Learn Discriminative Codebooksfor Scalable Landmark Classification

下一篇：SLAM++: Simultaneous Localisation and Mapping at the Level of Objects

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...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...