arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15680cs.LGstat.ML
收藏

机器学习中的建模泛化:方法论和计算研究

Modeling Generalization in Machine Learning: A Methodological and Computational Study

Cambridge University(剑桥大学);Politecnico di Torino(都灵理工大学);Université Paris-Saclay(巴黎萨克雷大学);INRAE(法国国家农业食品与环境研究院)

Pietro Barbiero, Giovanni Squillero, Alberto Tonda

摘要:

随着机器学习越来越多地为公众所用,理论问题正在转变为紧迫的实际问题。可能,最相关的问题之一是评估我们对信任机器学习预测的信心。在许多现实世界的情况下,最重要的是估计机器学习算法的泛化能力,即,根据目标问题的特征,对未知数据进行准确预测。在这项工作中,我们进行了109个公开的分类数据集的荟萃分析,建模机器学习泛化作为各种数据集特征的函数,范围从样本数量的内在维度,从类的功能偏度评估测试样本落在训练集的凸包之外的$F1$。实验结果证明了使用训练数据的凸包的概念在评估机器学习泛化中的相关性,通过强调内插和外推预测之间的差异。除了几个可预测的相关性,我们观察到出乎意料的弱关联之间的泛化能力的机器学习模型和所有指标的维度,从而挑战的共同假设,\textit{curse of dimensionality}可能会损害泛化机器学习。

英文摘要:

As machine learning becomes more and more available to the general public, theoretical questions are turning into pressing practical issues. Possibly, one of the most relevant concerns is the assessment of our confidence in trusting machine learning predictions. In many real-world cases, it is of utmost importance to estimate the capabilities of a machine learning algorithm to generalize, i.e., to provide accurate predictions on unseen data, depending on the characteristics of the target problem. In this work, we perform a meta-analysis of 109 publicly-available classification data sets, modeling machine learning generalization as a function of a variety of data set characteristics, ranging from number of samples to intrinsic dimensionality, from class-wise feature skewness to $F1$ evaluated on test samples falling outside the convex hull of the training set. Experimental results demonstrate the relevance of using the concept of the convex hull of the training data in assessing machine learning generalization, by emphasizing the difference between interpolated and extrapolated predictions. Besides several predictable correlations, we observe unexpectedly weak associations between the generalization ability of machine learning models and all metrics related to dimensionality, thus challenging the common assumption that the \textit{curse of dimensionality} might impair generalization in machine 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。

↑