arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.00658cs.LGcs.AIstat.ML
收藏

缺失数据下线性生成数据的线性预测:不一致性及解决方法

Linear predictor on linearly-generated data with missing values: non consistency and solutions

Université Paris-Saclay(巴黎萨克雷大学);Inria(法国国家信息与自动化研究所);CEA(法国原子能和替代能源委员会);CNRS/IN2P3(法国国家科学研究中心/国家核物理与粒子物理研究所);IJCLab(拉兹霍夫斯基物理实验室);Ecole Polytechnique(巴黎综合理工学院);IP Paris(巴黎理工学院);Mila(米拉人工智能研究所);McGill University(麦吉尔大学)

Marine Le Morvan, Nicolas Prost, Julie Josse, Erwan Scornet, Gaël Varoquaux

摘要:

我们考虑在数据有缺失值时构建预测器。我们研究了非常简单的情况下,预测的目标是一个线性函数的充分观察到的数据,我们表明,在缺失值的存在下,最佳的预测可能不是线性的。在特定的高斯情况下,它可以被写为观测数据和各种缺失值指标之间的多路交互的线性函数。由于其内在的复杂性,我们研究了一个简单的近似,并证明了有限样本的泛化范围,突出了每种方法表现最好的制度。然后,我们证明了具有ReLU激活函数的多层感知器可以是一致的,并且可以在真实模型和近似值之间进行良好的权衡。我们的研究强调了有趣的模型家族,这些模型有利于根据可用数据量拟合缺失值。

英文摘要:

We consider building predictors when the data have missing values. We study the seemingly-simple case where the target to predict is a linear function of the fully-observed data and we show that, in the presence of missing values, the optimal predictor may not be linear. In the particular Gaussian case, it can be written as a linear function of multiway interactions between the observed data and the various missing-value indicators. Due to its intrinsic complexity, we study a simple approximation and prove generalization bounds with finite samples, highlighting regimes for which each method performs best. We then show that multilayer perceptrons with ReLU activation functions can be consistent, and can explore good trade-offs between the true model and approximations. Our study highlights the interesting family of models that are beneficial to fit with missing values depending on the amount of data available.

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。

↑