Relative deviation learning bounds and generalization with unbounded loss functions
Annals of Mathematics and Artificial Intelligence(2019)
摘要
We present an extensive analysis of relative deviation bounds, including detailed proofs of two-sided inequalities and their implications. We also give detailed proofs of two-sided generalization bounds that hold in the general case of unbounded loss functions, under the assumption that a moment of the loss is bounded. We then illustrate how to apply these results in a sample application: the analysis of importance weighting.
更多查看译文
关键词
Generalization bounds,Learning theory,Unbounded loss functions,Relative deviation bounds,Importance weighting,Unbounded regression,Machine learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要