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 2005.10674cs.LGcs.AIstat.ML
收藏

约束机器学习的正则化方法分析

An Analysis of Regularized Approaches for Constrained Machine Learning

University of Bologna(博洛尼亚大学)

Michele Lombardi, Federico Baldo, Andrea Borghesi, Michela Milano

摘要:

介绍了在机器学习(ML)中注入约束的基于正则化的方法,以通过专家知识改进预测模型。我们解决了在损失(学习器的准确性)和正则化项(约束满足的程度)之间找到正确平衡的问题。本文的主要结果是正式证明,这种类型的方法不能保证找到所有的最优解。特别是,在非凸的情况下,可能有最优的约束问题,不对应于任何乘数值。

英文摘要:

Regularization-based approaches for injecting constraints in Machine Learning (ML) were introduced to improve a predictive model via expert knowledge. We tackle the issue of finding the right balance between the loss (the accuracy of the learner) and the regularization term (the degree of constraint satisfaction). The key results of this paper is the formal demonstration that this type of approach cannot guarantee to find all optimal solutions. In particular, in the non-convex case there might be optima for the constrained problem that do not correspond to any multiplier value.

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。

↑