A category theory framework for Bayesian learning

A category theory framework for Bayesian learning
复制标题

贝叶斯学习的范畴论框架

DOI:
--
复制
发表时间:
2021
期刊:
ArXiv
影响因子:
--
通讯作者:
John Welliaveetil
John Welliaveetil
中科院分区:
--
文献类型:
--
作者:
Kotaro Kamiya;John Welliaveetil

文献摘要

参考文献

被引文献

相似文献

受Spivak、Fong和Cruttwell等人的基础著作启发,我们引入了一个分类框架来形式化贝叶斯推理和学习。在这里起作用的两个关键思想是贝叶斯反演和函子GL的概念,由Cruttwell等人构造。在这种情况下,我们发现贝叶斯学习是学习范式的最简单的情况。然后,我们得到分类配方的批量和顺序贝叶斯更新,同时也验证了这两个在一个特定的例子中相吻合。
Inspired by the foundational works by Spivak and Fong and Cruttwell et al., we introduce a categorical framework to formalize Bayesian inference and learning. The two key ideas at play here are the notions of Bayesian inversions and the functor GL as constructed by Cruttwell et al.. In this context, we find that Bayesian learning is the simplest case of the learning paradigm. We then obtain categorical formulations of batch and sequential Bayes updates while also verifying that the two coincide in a specific example.
DOI: --
发表时间: 2008
期刊:
影响因子: --
作者:
渡辺有祐;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次;福水健次
通讯作者: 福水健次