arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1408.0838cs.LGcs.NAmath.NAmath.OCstat.ML
收藏

通过数学规划估计最大可能的约束关系

Estimating Maximally Probable Constrained Relations by Mathematical Programming

Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Lizhen Qu, Bjoern Andres

AI总结:

本文提出了一种概率测度家族,用于联合抽象多标签分类、相关聚类和排序问题,通过数学规划方法解决半监督学习。

摘要:

估计约束关系是机器学习中的基本问题。特殊情形包括分类、聚类和排序。本文贡献了一种在两个有限非空集合之间所有关系的概率测度家族,提供多标签分类、相关聚类和排序的联合抽象。给定相关和不相关配对的训练集,估计最大可能测度是一个凸优化问题。给定测度估计最大可能关系是一个01线性规划问题,对于映射可在线性时间内解决,而对于等价关系和线性顺序则是NP难问题。实验显示了所有三种情况的实用解决方案。最后,联合估计最大可能测度和关系被提出为混合整数非线性规划问题。此方法为半监督学习提供了数学规划的途径。

英文摘要:

Estimating a constrained relation is a fundamental problem in machine learning. Special cases are classification (the problem of estimating a map from a set of to-be-classified elements to a set of labels), clustering (the problem of estimating an equivalence relation on a set) and ranking (the problem of estimating a linear order on a set). We contribute a family of probability measures on the set of all relations between two finite, non-empty sets, which offers a joint abstraction of multi-label classification, correlation clustering and ranking by linear ordering. Estimating (learning) a maximally probable measure, given (a training set of) related and unrelated pairs, is a convex optimization problem. Estimating (inferring) a maximally probable relation, given a measure, is a 01-linear program. It is solved in linear time for maps. It is NP-hard for equivalence relations and linear orders. Practical solutions for all three cases are shown in experiments with real data. Finally, estimating a maximally probable measure and relation jointly is posed as a mixed-integer nonlinear program. This formulation suggests a mathematical programming approach to semi-supervised 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。

↑