基于领域和区域的机器学习性能抗协变量移位能力评估（英文版）

英文标题：A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift中文摘要：本文研究了异变转移对传统机器学习模型性能的影响，通过对概率密度函数域的区域进行分类器性能评估，发现在二维分类问题中，随机森林算法表现最好，在高维实验中，模型主要受到分类函数复杂度的影响，对高密度区域呈现出高偏差的性质。英文摘要：Most machine learning methods assume that the input data distribution is thesame in the training and testing phases. However, in practice, thisstationarity is usually not met and the distribution of inputs differs, leadingto unexpected performance of the learned model in deployment. The issue i