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 2409.09078stat.MLcs.LG
收藏

主动学习中的泛化误差界

Bounds on the Generalization Error in Active Learning

Universität Hamburg(汉堡大学)

Vincent Menden, Yahya Saleh, Armin Iske

AI总结:

该研究推导主动学习的泛化误差上界,建立经验风险最小化原则,验证结合信息性与代表性查询策略的优势,关联不同场景与对应上界,证明正则化技术是界成立的充分条件,为查询算法构建与评估提供理论支撑。

摘要:

我们通过推导一系列泛化误差上界,建立了主动学习的经验风险最小化原则。与经验观察一致,这些界表明,结合信息性和代表性查询策略可以得到更优的查询算法,其中代表性使用积分概率度量来评估。为便于这些界在实际中的应用,我们将以损失函数和假设类为特征的多种主动学习场景与其对应的上界进行了系统关联。我们的结果表明,用于约束各类假设类复杂度的正则化技术是确保这些界成立的充分条件。本工作为主动学习中查询算法的原则性构建与经验质量评估提供了支撑。

英文摘要:

We establish empirical risk minimization principles for active learning by deriving a family of upper bounds on the generalization error. Aligning with empirical observations, the bounds suggest that superior query algorithms can be obtained by combining both informativeness and representativeness query strategies, where the latter is assessed using integral probability metrics. To facilitate the use of these bounds in application, we systematically link diverse active learning scenarios, characterized by their loss functions and hypothesis classes to their corresponding upper bounds. Our results show that regularization techniques used to constraint the complexity of various hypothesis classes are sufficient conditions to ensure the validity of the bounds. The present work enables principled construction and empirical quality-evaluation of query algorithms in active learning.

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。

↑