( events)   Timezone: »  
Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #104
Learning Beam Search Policies via Imitation Learning
Renato Negrinho · Matthew Gormley · Geoffrey Gordon

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. 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.