arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1811.00512stat.MLcs.AIcs.LG
收藏

通过模仿学习学习波束搜索策略

Learning Beam Search Policies via Imitation Learning

Carnegie Mellon University(卡内基梅隆大学);Microsoft Research(微软研究院)

Renato Negrinho, Matthew R. Gormley, Geoffrey J. Gordon

摘要:

波束搜索广泛用于结构化预测问题的近似解码。模型通常在测试时使用梁,但在训练时忽略它的存在,因此不明确地学习如何使用梁。我们开发了一个统一的元算法,用于使用模仿学习来学习波束搜索策略。在我们的设置中,光束是模型的一部分,而不仅仅是近似解码的伪影。我们的元算法捕获了现有的学习算法,并提出了新的算法。它还让我们展示了学习波束搜索策略的新的无遗憾保证。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑