BriefGPT.xyz
Oct, 2013
相对偏差学习界限与具有无界损失函数的泛化
Relative Deviation Learning Bounds and Generalization with Unbounded Loss Functions
HTML
PDF
Corinna Cortes, Spencer Greenberg, Mehryar Mohri
TL;DR
本文详细证明了相对偏差界限的双侧不等式及其影响，并在损失函数的无界情况下给出了双侧广义界限的证明，其中假设损失的某一时刻有界。这些界限对于重要性加权和其他学习任务如无界回归的分析非常有用。
Abstract
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
→