Constant-memory algorithms, also loosely called Markov chains, power the vast majority of probabilistic inference and machine learning applications today. A lot of progress has been made in constructing user-friendly APIs around these algorithms. Such APIs, however, rarely make it easy to research new algorithms of this type. In this work we present FunMC, a minimal Python library for doing methodological research into algorithms based on Markov chains. FunMC is not targeted toward data scientists or others who wish to use MCMC or optimization as a black box, but rather towards researchers implementing new Markovian algorithms from scratch.
翻译:常数模拟算法, 也叫Markov 链, 使绝大多数的概率推论和机器学习应用今天都具有力量。 在围绕这些算法建立方便用户的API方面已经取得了很大进展。 但是,这种API很少容易研究这种类型的新算法。 在这项工作中,我们介绍了FunMC, 一个最小的Python图书馆, 用来对基于Markov 链的算法进行方法研究。 FunMC并不是针对那些希望使用 MCMC 或优化为黑盒的数据科学家或其他人,而是针对从零开始实施新的Markovian 算法的研究人员。