English

Train and Test Tightness of LP Relaxations in Structured Prediction

Machine Learning 2016-04-28 v3 Artificial Intelligence Machine Learning

Abstract

Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently, by solving an integer linear program. Because of the complex scoring functions required to obtain accurate predictions, both learning and inference typically require the use of approximate solvers. We propose a theoretical explanation to the striking observation that approximations based on linear programming (LP) relaxations are often tight on real-world instances. In particular, we show that learning with LP relaxed inference encourages integrality of training instances, and that tightness generalizes from train to test data.

Keywords

Cite

@article{arxiv.1511.01419,
  title  = {Train and Test Tightness of LP Relaxations in Structured Prediction},
  author = {Ofer Meshi and Mehrdad Mahdavi and Adrian Weller and David Sontag},
  journal= {arXiv preprint arXiv:1511.01419},
  year   = {2016}
}

Comments

To appear in ICML 2016