arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 1110.2136cs.LG
收藏

基于光滑相对遗憾近似的主动学习及其应用

Active Learning Using Smooth Relative Regret Approximations with Applications

Technion IIT(以色列理工学院);NYU(纽约大学)

Nir Ailon, Ron Begleiter, Esther Ezra

摘要:

Hanneke的不一致系数已成为证明主动学习率的中心数据独立不变量。已经以各种方式表明,具有低复杂度的概念类连同最优解处的不一致系数上的界限允许优于被动学习的主动学习率。我们提出了一个不同的工具池为基础的主动学习,遵循从存在一定的统一版本的低分歧系数,但不等于它。事实上,我们提出了两个基本的主动学习问题的重大利益,我们的方法允许非平凡的主动学习的界限。然而,任何通用的方法依赖于不一致系数的界限,只是不能保证任何有用的界限,这些问题。我们使用的工具是基于学习者的能力,以计算任何假设的损失和一些固定的“关键”假设之间的差异的估计,以在最多$\eps$倍的绝对误差内。

英文摘要:

The disagreement coefficient of Hanneke has become a central data independent invariant in proving active learning rates. It has been shown in various ways that a concept class with low complexity together with a bound on the disagreement coefficient at an optimal solution allows active learning rates that are superior to passive learning ones. We present a different tool for pool based active learning which follows from the existence of a certain uniform version of low disagreement coefficient, but is not equivalent to it. In fact, we present two fundamental active learning problems of significant interest for which our approach allows nontrivial active learning bounds. However, any general purpose method relying on the disagreement coefficient bounds only fails to guarantee any useful bounds for these problems. The tool we use is based on the learner's ability to compute an estimator of the difference between the loss of any hypotheses and some fixed "pivotal" hypothesis to within an absolute error of at most $\eps$ times the

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。

↑