arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2310.00511cs.LGmath.STstat.TH
收藏

面向代价敏感分类的非参数主动学习

Nonparametric active learning for cost-sensitive classification

University of Mons(蒙斯大学)

Boris Ndjia Njike, Xavier Siebert

AI总结:

本文提出一种用于代价敏感分类的通用非参数主动学习算法,通过置信界和最小代价查询实现最优交互复杂度,并证明其相对被动学习的增益及上下界近最优性。

摘要:

代价敏感学习是一类常见的机器学习问题,其中不同的预测错误会产生不同的代价。本文设计了一种用于代价敏感分类的通用非参数主动学习算法。基于为每个标签的期望预测代价函数构造置信界,该算法按顺序选择信息量最大的向量点,随后仅查询可能成为最小值的预测代价,并与这些点进行交互。我们证明,就与特征向量空间的交互次数而言,该算法达到最优收敛速率。此外,在一般形式的 Tsybakov 噪声假设下,其相对于相应被动学习的增益由决策边界的概率质量显式刻画。我们还通过给出匹配(至多相差对数因子)的下界,证明了所得上界的近最优性。

英文摘要:

Cost-sensitive learning is a common type of machine learning problem where different errors of prediction incur different costs. In this paper, we design a generic nonparametric active learning algorithm for cost-sensitive classification. Based on the construction of confidence bounds for the expected prediction cost functions of each label, our algorithm sequentially selects the most informative vector points. Then it interacts with them by only querying the costs of prediction that could be the smallest. We prove that our algorithm attains optimal rate of convergence in terms of the number of interactions with the feature vector space. Furthermore, in terms of a general version of Tsybakov's noise assumption, the gain over the corresponding passive learning is explicitly characterized by the probability-mass of the boundary decision. Additionally, we prove the near-optimality of obtained upper bounds by providing matching (up to logarithmic factor) lower bounds.

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。

↑