Artifical Intelligence Seminar

  • Ph.D. Student
  • Machine Learning Department
  • Carnegie Mellon University

Learning Beam Search Policies via Imitation Learning

Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. % The Solution: our meta-algorithm We develop an unifying meta-algorithm for learning beam search policies using imitation learning. In our setting, the beam is part of the model, and not just an artifact of approximate decoding. Our meta-algorithm captures existing learning algorithms and suggests new ones. It also lets us show novel no-regret guarantees for learning beam search policies.

The AI Seminar is generously sponsored by Apple

For More Information, Please Contact: