arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02822cs.LG
收藏

低后悔主动学习

Low-Regret Active learning

MIT(麻省理工学院);University of Haifa(海法大学)

Cenk Baykal, Lucas Liebenwein, Dan Feldman, Daniela Rus

摘要:

我们开发了一种在线学习算法,用于识别对训练信息量最大的未标记数据点(即,主动学习)。通过将主动学习问题公式化为睡眠专家问题的预测,我们提供了一个后悔最小化框架,用于识别与任何给定的信息量定义相关的数据。受主动学习中集成成功的启发,我们将遗憾定义为可以访问无限大集成的全能算法。我们工作的核心是为睡眠专家提供一种高效的算法,该算法经过量身定制,可以在简单的情况下实现低遗憾,同时对对抗性的情况保持弹性。低遗憾意味着我们可以证明与集成方法\emph{without the computational burden of having to train an ensemble}竞争。这与最先进的主动学习方法形成对比,这些方法绝大多数基于贪婪选择,因此无法确保在具有大量噪声的问题实例中具有良好的性能。我们提出的实证结果表明,我们的方法(i)实例化的信息量的措施始终优于其贪婪的同行和(ii)可靠地优于均匀采样在现实世界的情况下。

英文摘要:

We develop an online learning algorithm for identifying unlabeled data points that are most informative for training (i.e., active learning). By formulating the active learning problem as the prediction with sleeping experts problem, we provide a regret minimization framework for identifying relevant data with respect to any given definition of informativeness. Motivated by the successes of ensembles in active learning, we define regret with respect to an omnipotent algorithm that has access to an infinity large ensemble. At the core of our work is an efficient algorithm for sleeping experts that is tailored to achieve low regret on easy instances while remaining resilient to adversarial ones. Low regret implies that we can be provably competitive with an ensemble method \emph{without the computational burden of having to train an ensemble}. This stands in contrast to state-of-the-art active learning methods that are overwhelmingly based on greedy selection, and hence cannot ensure good performance across problem instances with high amounts of noise. We present empirical results demonstrating that our method (i) instantiated with an informativeness measure consistently outperforms its greedy counterpart and (ii) reliably outperforms uniform sampling on real-world scenarios.

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。

↑