arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.07265cs.LGstat.ML
收藏

搜索改善了主动学习的标签

Search Improves Label for Active Learning

Yahoo Research(雅虎研究院);Columbia University(哥伦比亚大学);Microsoft Research(微软研究院);University of California, San Diego(加利福尼亚大学圣地亚哥分校)

Alina Beygelzimer, Daniel Hsu, John Langford, Chicheng Zhang

摘要:

我们研究了主动学习与访问两个不同的预言:标签(这是标准的)和搜索(这不是)。搜索预言机模拟了人类搜索数据库以播种或反例现有解决方案的情况。搜索比标签更强大,同时在许多情况下自然实现。我们表明,使用这两个预言机的算法可以提供指数级大的问题依赖的标签单独的改进。

英文摘要:

We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human searches a database to seed or counterexample an existing solution. Search is stronger than Label while being natural to implement in many situations. We show that an algorithm using both oracles can provide exponentially large problem-dependent improvements over Label alone.

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。

↑