arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.03753cs.LGstat.ML
收藏

改进的判别性特征反馈学习鲁棒算法

Improved Robust Algorithms for Learning with Discriminative Feature Feedback

Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Sivan Sabato

AI总结:

本研究针对判别性特征反馈模型提出新的鲁棒交互式学习算法,在对抗性设置中降低错误界对异常次数的依赖,并在随机设置中首次实现多项式样本复杂度收敛。

摘要:

判别性特征反馈(Discriminative Feature Feedback)是由Dastupta等人(2018)提出的一种设置,它为基于人类教师提供的特征解释的交互式学习提供了一种协议。这些特征用于区分可能相似实例对之间的标签。该研究表明,在这种模型中学习相比在标准基于标签的交互式学习模型中学习,可以具有相当大的统计和计算优势。在本工作中,我们为判别性特征反馈模型提供了新的鲁棒交互式学习算法,其错误界显著低于先前针对该设置的鲁棒算法。在对抗性设置中,我们将对协议异常次数的依赖从二次降低到线性。此外,我们为稍微更受限的模型提供了一种算法,该算法对于具有许多异常的大型模型获得了更小的错误界。在随机设置中,我们提供了第一个以多项式样本复杂度收敛到异常率的算法。我们针对随机设置的算法和分析涉及一个新的构造,我们称之为特征影响(Feature Influence),它可能具有更广泛的适用性。

英文摘要:

Discriminative Feature Feedback is a setting proposed by Dastupta et al. (2018), which provides a protocol for interactive learning based on feature explanations that are provided by a human teacher. The features distinguish between the labels of pairs of possibly similar instances. That work has shown that learning in this model can have considerable statistical and computational advantages over learning in standard label-based interactive learning models. In this work, we provide new robust interactive learning algorithms for the Discriminative Feature Feedback model, with mistake bounds that are significantly lower than those of previous robust algorithms for this setting. In the adversarial setting, we reduce the dependence on the number of protocol exceptions from quadratic to linear. In addition, we provide an algorithm for a slightly more restricted model, which obtains an even smaller mistake bound for large models with many exceptions. In the stochastic setting, we provide the first algorithm that converges to the exception rate with a polynomial sample complexity. Our algorithm and analysis for the stochastic setting involve a new construction that we call Feature Influence, which may be of wider applicability.

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。

↑