BriefGPT.xyz
Nov, 2021
关于可计算连续特征学习的研究
On computable learning of continuous features
HTML
PDF
Nathanael Ackerman, Julian Asilis, Jieqi Di, Cameron Freer, Jean-Baptiste Tristan
TL;DR
定义可计算的计算度量空间上二元分类的可计算PAC学习，提供解决ERM学习器可计算性的充分条件，限制ERM学习器的Weihrauch度，展示一种假设类，尽管底层类具有PAC可学性，但它不允许具有可计算采样函数的任何适当的可计算PAC学习器。
Abstract
We introduce definitions of
computable pac learning
for
binary classification
over computable metric spaces. We provide sufficient conditions for learners that are
→