TL;DR本文针对机器学习中数据采集的困难和对泛化理解的缺乏,提出一种风险单调且效率较高的学习算法,解决了 Viering et al. 2019 提出的风险曲线非单调性的问题,同时提出了专门针对马尔可夫差分序列等非独立同分布的过程的经验 Bernstein 集中不等式的新方法。
Abstract
Acquisition of data is a difficult task in many applications of machine
learning, and it is only natural that one hopes and expects the population risk
to decrease (better performance) monotonically with increasing data points. It
turns out, somewhat surprisingly, that this is not the