离群者会破坏协作吗?
Do Outliers Ruin Collaboration?
摘要:
我们考虑从$n$不同的数据源中学习一个二元分类器的问题,其中至多有一个$η$分数是对抗的。开销被定义为在此设置中学习的样本复杂度与在单个数据分布上学习相同假设类的样本复杂度之间的比率。我们提出了一种算法,实现了$O(ηn + \ln n)$开销,这被证明是最坏情况下的最佳。我们还讨论了潜在的挑战,设计一个计算效率高的学习算法与小开销。
英文摘要:
We consider the problem of learning a binary classifier from $n$ different data sources, among which at most an $η$ fraction are adversarial. The overhead is defined as the ratio between the sample complexity of learning in this setting and that of learning the same hypothesis class on a single data distribution. We present an algorithm that achieves an $O(ηn + \ln n)$ overhead, which is proved to be worst-case optimal. We also discuss the potential challenges to the design of a computationally efficient learning algorithm with a small overhead.
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。