Agnostic active learning
Agnostic active learning
复制标题
DOI：
10.1145/1143844.1143853
复制
发表时间：
2006-06
期刊：
影响因子：
--
通讯作者：
Maria-Florina Balcan;A. Beygelzimer;J. Langford
中科院分区：
文献类型：
--
作者：
Maria-Florina Balcan;A. Beygelzimer;J. Langford
我们陈述并分析了第一个主动学习算法，该算法在任意形式的噪声存在下工作。该算法 A2（用于不可知主动）仅依赖于样本是独立同分布的假设。来自固定分布。我们表明，对于之前在可实现的情况下考虑的几种设置，A2 相对于监督学习的通常样本复杂性实现了指数级改进（即仅需要 O (ln 1/ε) 个样本即可找到 ε 最优分类器）。这些包括学习阈值分类器和学习关于在单位球体上均匀的输入分布的同质线性分离器。
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the assumption that the samples are drawn i.i.d. from a fixed distribution. We show that A2 achieves an exponential improvement (i.e., requires only O (ln 1/ε) samples to find an ε-optimal classifier) over the usual sample complexity of supervised learning, for several settings considered before in the realizable case. These include learning threshold classifiers and learning homogeneous linear separators with respect to an input distribution which is uniform over the unit sphere.